See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/305321699

On recent advances in PV output power forecast

Article  in  Solar Energy · July 2016

DOI: 10.1016/j.solener.2016.06.073

CITATIONS READS

51 779

3 authors:

Muhammad Qamar Raza Mithulananthan Nadarajah

The University of Queensland The University of Queensland
22 PUBLICATIONS   221 CITATIONS    254 PUBLICATIONS   4,778 CITATIONS   

SEE PROFILE SEE PROFILE

C. Ekanayake
The University of Queensland
91 PUBLICATIONS   787 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Micro-grid Stability View project

Intelligent Network Integration of DG View project

All content following this page was uploaded by Muhammad Qamar Raza on 28 December 2017.

The user has requested enhancement of the downloaded file.

 Solar Energy 136 (2016) 125–144

Contents lists available at ScienceDirect

Solar Energy
journal homepage: www.elsevier.com/locate/solener

Review

On recent advances in PV output power forecast

Muhammad Qamar Raza ⇑, Mithulananthan Nadarajah, Chandima Ekanayake
Power and Energy System Group, School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD 4072, Australia

a r t i c l e i n f o a b s t r a c t

Article history: In last decade, the higher penetration of renewable energy resources (RES) in energy market was encour-
Received 25 December 2015 aged by implementing the energy polices in several developed and developing countries due to increas-
Received in revised form 28 June 2016 ing environmental concerns. Among wide range of RES, Photovoltaic (PV) electricity generation get higher
Accepted 29 June 2016
attention by researcher, energy policy makers and power production companies due to its economic and
environmental benefits. Therefore, a large PV penetration was observed in energy market with rapid
growth in the last decade. The PV output power is highly uncertain due to several meteorological factors
Keywords:
such as temperature, wind speed, cloud cover, atmospheric aerosol levels and humidity level. The inher-
Photovoltaic
Artificial intelligence (AI)
ent variability of PV output power creates different issues directly or indirectly for power grid such as
Regressive techniques power system control and reliability, reserves cost, dispatchable and ancillary generation, grid integra-
PV output forecasting tion and power planning. Therefore, there is need to accurately forecast the PV output over the spectrum
Hybrid forecast models of forecast horizon at different chronological scales. In this paper, a comprehensive and systematic review
Artificial neural network (ANN) of PV output power forecast models were provided. This review covers the different factors affecting PV
Auto-regressive moving average forecast, PV output power profile and performance matrices to evaluate the forecast model. The critical
Fuzzy Logic analysis regressive and artificial intelligence based forecast models are also presented. In addition, the
Persistence method
potential benefits of hybrid techniques for PV forecast models are also thoroughly discussed.
Statistical methods
Ó 2016 Elsevier Ltd. All rights reserved.

Contents

1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 126
2. Factors affecting PV output power forecast . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128
2.1. Forecast horizon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128
2.2. Forecast model performance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128
2.3. Preprocessing of input data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128
2.4. Forecast model inputs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129
3. Solar output power profile . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129
3.1. UQ center array PV output profile . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129
4. Classification of forecast techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132
4.1. Persistence forecast . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132
4.2. Physical models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132
4.3. Statistical techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132
4.4. Linear models or time series models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133
4.4.1. ARMA model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133
4.4.2. ARIMA techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133
4.4.3. CARDS model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133

Abbreviations: AI, artificial intelligence; AM, air mass; ANN, artificial neural network; AR, auto-regressive; ARIMA, Auto-Regressive Integrated Moving Average; ARIMAX,
ARIMA exogenous; ARMA, Auto-Regressive Moving Average; ARMAX, ARMA-exogenous; DR, Demand response; BP, back propagation; CPV, concentrated PV; DHI, diffuse
horizontal irradiance; DNI, direct normal irradiance; GA, genetic algorithm; GHI, global horizontal irradiance; HS, hybrid system; IEA, International Energy Agency; ISO,
independent system operator; LMS, least means square; MA, moving average; MAE, Mean Absolute Error; MAPE, mean absolute percent error; MBE, Mean Bias Error; MLP,
multi-layer perceptron; NAR, non-linear AR; NARMAX, non-linear ARMA exogenous; NARX, non-linear AR exogenous; NWP, numerical weather prediction; PV, Photovoltaic.
⇑ Corresponding author.
E-mail addresses: Qamar.raza@uq.edu.au (M.Q. Raza), mithulan@itee.uq.edu.au (M. Nadarajah), chandima@itee.uq.edu.au (C. Ekanayake).

http://dx.doi.org/10.1016/j.solener.2016.06.073
0038-092X/Ó 2016 Elsevier Ltd. All rights reserved.
126 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

4.5. Artificial intelligence techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134

4.6. Significance of ANN approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134
4.6.1. Artificial neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134
4.6.2. Artificial neural network architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134
4.6.3. Activation function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 135
4.6.4. Multi layer perceptrons neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 135
4.6.5. Radial basis function network (RBFNN) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 135
4.6.6. Recurrent neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 135
4.6.7. Feed forward neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 136
4.6.8. Feedback neural network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 137
4.7. ANN and classical time series models comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 137
4.8. Hybrid models for PV output forecast . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140
5. Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141
6. Forecast model performance evaluations matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141
7. Conclusions and future work. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142
References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143

1. Introduction
In last decades, the global energy demand increased steadily
with rapid growth in world population. The energy demand is at
the higher level ever before and most of the fossil resources are
the edge of depletion due to excess usage. Therefore, ‘‘how to
meet the 21 century energy demand” is the hot topic of discussion
among the governments, researcher, scientists and energy policy
makers in developed and developing countries. In addition, other
concern is rapid changes in environmental and climatic conditions
(i.e. global warming, depletion of ozone layer, etc.). Keep in view
the energy issue, International Energy Agency (IEA) raised the
concerned namely energy security, economic efficiency, and envi-
ronmental protection, which are known as ‘‘3Es” ((IEA), 2007).
Therefore, concentrated efforts have made to reduce the emission
of CO2 and minimum reliance on fossil fuels in order to achieve
the 3Es objectives. Serval countries have been made efforts to meet
the 3E objectives which are align with IEA guidelines and their
national energy targets.
European union (EU) was decided to meet the energy targets by
2020 (Council, 2010). First target is to reduce the EU Green House
Gas (GHG) emission by 20% below the level of 1990. Secondly, the
contribution of renewable energy resources (RES) raise up to 20%.
Thirdly, reduction of energy usage by 20% in contrast with pro-
jected levels through energy efficiency measures. European Union
renewable energy directive set the RES production targets. It states
that, 30% total energy will be produced from RES generation by
2030. The target of RES generation contribution will be climbed
up to 100% by 2050 (Zervos et al., 2010). In addition, a high RES
contribution in existing power grid network is also expected by
the energy regulators of USA, Canada, Australia, China and India.
Among number of RES resources, solar and wind power generation
are more promising sources. They have higher potential for pene-
tration in energy market with greater degree of success. However,
solar generation get much more attention by the energy player,
investors and Government funding agencies in the last decade
because of its economic and environmental benefits.
Solar energy is feasible solution in order to meet the world
energy demand. A research study highlights that, earth received
approximately 1.8 ⁄ 1011 MW power from solar radiation at instant
(B.M. Shah et al., 2015). However, the present world energy con-
sumption requirement is less than the amount of energy received
from solar (Wengenmayr and Bührke, 2011). Fig. 1 depicts the
world solar energy map with solar hotspots. A huge potential for
solar power generation in different countries can be observed
those are above 45°N or below latitude 45°S. It can also
be observed, the Middle East, Mojave Desert (USA), the Chilean
Atacama Desert, the Sahara and Kalahari Deserts (Africa) and
North-western Australia are potential locations for large power
generation from solar PV technology.
Another research study (R. Shah et al., 2015) highlights that, the
electricity demand of Mediterranean, North African region and
entire Europe can be fulfilled by developing solar plants in Sahara
Desert. The red sea including different areas of Saudi Arabia and
Egypt are also among the highest potential sources for solar
energy. In addition, United States and Australia also have greater
potential to get benefit form solar energy than the world average.
Due to potential of solar energy, large penetration of solar PV is
expected in Australian energy sector in terms of rooftop PV, large
and small scale solar PV units. In last decade, the higher penetra-
tion of PV technology in energy market of different countries is
observed due its environmental and economic benefits
(Photovoltaics, 2012). These benefits are reduction in CO2 emis-
sion, minimum refinance of fossil fuel resources and Solar Photo-
voltaic (PV) plants consist of solar panels, which directly convert
the sunlight into electricity unlike power generation using rotating
generators. PV becomes more popular due to different promising
features such as modularity, low maintenance and operational
cost, longer lifetime, CO2 reduction and environmental cleanliness.
The energy generation capacity of solar plant varies due different
factors such as PV plant site, meteorological variables, solar tech-
nology and installation capacity.
Fig. 2 highlights the growth of world solar PV capacity in the
last decade. An exponential growth can be observed in global solar
PV capacity from 2004 to 2014. Global capacity was increased from
3.7 GW to 7 GW in three years (2004–2007). In contrast, it was
increased from 7 to 40 GW in next three years. In addition, a huge
growth in global solar PV capacity was observed in next couple of
years. For example, global was more than double in 2010 as com-
pared to 2008. Overall, global PV energy capacity was increased
from 3.7 to 177 GW in the last decade. A research study reports
that, the PV module have individual capacity from 100 W to
320 W (Omran). The PV technology still facing lot of challenges
for large penetration, in which intermittent and uncertain nature
of solar PV is more prominent. The PV output power is variable
mainly due to variations in solar radiations and amount received
solar by the solar panels.
With a remarkable growth of PV in last decade, the integration
of photovoltaic plants in current power network raise the different
technical and stability issues for the power system directly or indi-
rectly. These distress arises due to continuous change in solar
resource, temperature, PV output power, high energy storage cost,
grid reliability, seasonal and environmental changes (Denholm and
Margolis, 2007; Dixon et al., 2010). The implementation of PV
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 127

Fig. 1. The world solar energy map (Zhang et al., 2013).

200 manner with accurate PV forecast. The PV output forecast can be

divided into different categories based on forecast horizon such
180
as very short term, short term, medium term and long term PV out-
160 put forecast.
140 Short term PV output forecast can be utilized for automatic gen-
eration control (AGC), better unit dispatching, load balancing and
Power (GW)

120
100
80
60
40
20
0
2004 2005 2006 2007 2008 2009 2010 2011 2012
Year
Fig. 2. Global solar PV capacity from 2004 to 2014 (Zervos, 2015).
power network as back up supply without storage devices is not a
technical viable solution as it affects the grid stability due variable
output power. It is due to large variations in meteorological condi-
tions, which increase the uncertainty of PV output power.
Therefore, an accurate PV output forecast over the spectrum of
forecast horizon is required for independent power producing (IPP)
and managing companies or equivalent grid balancing authorities.
The accurate PV forecast will help IPP or power authorities for bet-
ter energy planning and management. In addition, accurate fore-
cast will be beneficial in terms of smart integration the PV
generation with current grid with higher system reliability
(Dixon et al., 2010; Rodriguez, 2010; Helman et al., 2010). There-
fore, the importance of PV output forecast is vital in order to
achieve higher penetration of solar power technology. It will also
contribute to minimize the reliance on fossil fuels resources. In
addition, grid regulation, power scheduling, unit commitment
and energy management system can be designed in effective
power plant operational management. ISO’s and utilities are more
interested in relatively longer forecast horizons for unit commit-
ment, load balancing and scheduling. The distribution and trans-
mission grids operational planning and balancing require the
spectrum of solar forecast for efficient management. It helps to grid
to reduce the ancillary costs associated with weather dependency
and deliver quality of energy. In addition, power gird stability of PV
integrated can be ensured with accurate PV forecast. It will
2013 2014
increase PV penetration in existing power grid network and help
to reduce of CO2 emission. From the grid prospective, reduction
of the power system operational costs is a main factor to design
accurate PV forecast models. PV output power forecast may also
part of smart grid (future generation power grids) energy manage-
ment system along with wind and load forecast.
A number of factors affecting on PV output power, which leads
to uncertain and unpredictable PV output pattern. Therefore, this is
essential to design a robust, intelligent and adaptive forecast
model which can accommodate the factors affecting on PV output
for higher forecast accuracy. The complexity of forecast model will
be increased by accommodating the different factors affecting on
the output such wind speed, irradiance, temperature, cloud cover,
and seasonal variations. Therefore, there is always need to trade off
the number of forecast model inputs and complexity by keeping in
view of forecast accuracy.
As a reminder the organization of the paper as fellows: Section 2
describes fundamental considerations for solar power generation.
Section 3 briefly illustrate the, solar output power profile of The
University of Queensland (UQ), Australia St. Lucia campus center
array. The preprocessing of input data and forecast model
performance evaluation matrices are elaborated in Sections 4 and
5. Section 6 reviews the regressive and artificial intelligence based
128 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
forecasting techniques with help of comprehensive tables. The
potential benefits of hybrid system for PV forecast application
are discussed in Section 7.
2. Factors affecting PV output power forecast
A number of variable are affecting on the output of PV forecast
model such as forecast horizon, forecast model input, performance
of prediction and data preprocessing applied as forecast model
input data. The forecast accuracy can be enhanced by accommo-
dating the factors affecting on the PV output as forecast model
inputs. These factors are described below.
2.1. Forecast horizon
The span of time into the future for which forecasts are to be
prepared called forecast horizon. There are no well-defined criteria
to classify the forecasting in different categories based on forecast
horizon. However, some researcher reports that, forecast can be
divided in three based on time horizon. According to Raza and
Khosravi (2015), electrical load forecasting can be divided into
three categories by most of researchers but some of them divided
it into four categories (Amral et al., 2007). Broadly, forecasting can
be divided in four major’s categories/types based on forecast hori-
zon as given below:
I. Long term forecast (1–10 year ahead).
II. Medium term forecast (1 month to 1 year ahead).
III. Short term forecast (1 h or several hours ahead to 1 day or
1 week ahead).
IV. Very short term forecast (1 min to several min ahead).
Some of the researcher consider the few seconds or 1 min to 1 h
or several hours (maximum 6 h) ahead forecast as very short term
forecast. However, some researcher considers as subclass of short
term forecast. However, majority of them enlist the very short
forecast as a separate class. In case of PV output forecast, short
term or very short term forecast is useful in order to design PV
integrated better energy management system, unit commitment,
power scheduling and dispatching. It is reported that for PV output
forecast, the prediction accuracy of the model varies by changing
the forecast horizon even with identical forecast model parame-
ters. In Lipperheide et al. (2015), research study analyze the perfor-
mance of PV output forecast model over the different forecast
horizon time such as 20, 40, and 60 . . . up to 180 s. The proposed
forecast model produce prediction error (rRMSE) in the range of
3.2–15.5% for forecast horizon from 20 to 180 s. In Lonij et al.
(2013) authors design a forecast model which produces the error
4.6% and 2.4% for 15 and 30 min forecast horizons, respectively.
It can be observed from above reported that the forecast error var-
ies with change in forecast horizon.
2.2. Forecast model performance
The PV output forecast accuracy is dependent on prediction
model performance. It is due to capability of individual forecast
model to handle the meteorological uncertainties. A number of sta-
tistical and artificial intelligence based forecast models are
designed to accurately forecast the PV output. Several research
studies have been reported to compare the performance of conven-
tional, statistical and ANN based forecast models. In Almonacid
et al. (2010) authors designed three different conventional mathe-
matical models for PV output forecast and compare with artificial
neural network (ANN). According to their findings, ANN based
model outperform than the conventional mathematical models in
terms of forecast accuracy and adaptability in uncertain meteoro-
logical conditions. A research study (Oudjana et al., 2013), purpose
a methodology to compare the ANN and regression model perfor-
mance for PV plant in the Ghardaia province of Algeria. ANN model
demonstrate higher forecast accuracy than the regression model
with solar radiation and temperature as independent variables.
In Almeida et al. (2015), authors analyze the PV output
forecast performance of five different models named as the
k-Nearest-Neighbour, Persistent model, the Autoregressive
Integrated Moving Average (ARIMA), ANNs and the hybrid Genetic
algorithm based ANN model for 1 MW PV plant in California. ANN
model produces less forecast error up to RMSE of 11.42 for 1-h ahead
forecast. However, the forecast accuracy further can be enhanced by
optimizing the ANN parameters using population based optimiza-
tion techniques. It can be concluded that, the forecast accuracy of
PV output forecast model varies by changing the forecast model. It
is due to performance of individual forecast model.
2.3. Preprocessing of input data
A number of PV output forecast model utilized the historical PV
output data as forecast model input. The historical PV output data
may contain different spikes and non-stationary components due
to uncertain and variable meteorological conditions. As a result,
these non-stationary and spikes in data will leads to higher fore-
cast error due to improper training. The historical PV output data
can be processed for smoothing. In addition, missing input data
points in historical data will also play a role to increase the forecast
error. Therefore, the forecast accuracy of model can be consider-
ably improved by input preprocessing. A number of techniques
were applied to preprocess the inputs of forecast model. The pre-
processed input data will significantly reduce computational cost
of forecast model by learning the historical pattern in better way.
Stationary, trend free time series, historical lag identification and
normalization are useful techniques to preprocess the input data
for accurate PV output forecast. Time series of the clearness or
clear-sky index are used in different research studies for prepro-
cessing as reported in Bacher et al. (2009) and Kemmoku et al.
(1999).
However, some of research doesn’t agree with huge impact of
clearness or clear-sky index in enhancement of forecast accuracy
(Sfetsos and Coonick, 2000). This study reports that, time series
of the clearness or clear-sky index is random in nature and varies
due to different meteorological factors. Therefore, it does not pro-
vide strong learning basis to prediction model. It may lead to poor
forecast accuracy along with increased computational cost. The
forecast results of this study demonstrates that, the preprocessed
solar irradiance data is more effective to use as forecast model.
In Cao and Cao (2006), Wavelets transform (WT) technique was
used for preprocessing of input data. The inputs of forecast model
are split in different frequency components. These components
were used forecast model inputs. In Reikard (2009), solar irradi-
ance was used as input of model due to its impact on the PV out-
put. In addition, statistical tool was used to remove the seasonality
trend in input data and it helps to increase the learning perfor-
mance of the model. However, it is difficult to find the accurate
trend of daily solar irradiance data series due unpredictable noise.
Some other research studies, analyze the performance of forecast
model by applying a trend and de trend techniques for solar irradi-
ance data (Baig et al., 1991; Kaplanis, 2006). Generally, the PV out-
put power follow the solar irradiance patter up to certain extent.
Cyclic behavior of solar radiation can be predicted with high
degree of accuracy by using Fourier series as predictor. This tech-
nique is able predict the solar irradiance by combing the different
significant frequencies. According to Boland (1995, 2008), the daily
time series profile of solar irradiance can be constructed effectively
constructed by capturing the yearly and intraday cycles. In order to
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 129

analyze the performance of de trend model, Artificial Intelligence

based techniques were utilized in literature. Augmented Dickey–
Fuller (ADF) test is used to measure the performance of de trend
series which can be utilized as input to the forecast model. For time
series data, ADF is treated as test. In realization process, time series
data contains unit root which is tested using ADF technique as
given in Eq. (1).

X t ¼ aX t þ Z t ð1Þ


where a = 1 and Z t  WN 0; r 2Z , WN represents the time series
white noise. Preprocessing techniques were also applied to different
other forecast application such as load, electricity price and wind
forecast. These results demonstrate the potential benefits of prepro-
cessing in terms of forecast accuracy.

2.4. Forecast model inputs

Fig. 3. PV center array at UQ St. Lucia campus.
Forecast model inputs also play a vital in order to enhance the
predication accuracy and model performance in terms of computa-
tional complexity and cost. Predication error of forecast model is Table 1
increased due to improper selection of forecast model inputs. UQ center solar array specification.
Therefore, PV output forecast model unable to correctly map the
Parameters Specification
all input variables as a forecast output due to poor selection of
essential influential variables. In De Giorgi et al. (2014), authors Site longitude 153°000 54.800 E
Site latitude 27°290 4500 S
design a PV output forecast model with different input vectors Height above sea level Height above sea level: 28 m
and analyze the impact of these input vectors on the output perfor- Type of installation Rooftop installation (elevated)
mance of the model. In this study, three types of vectors are Tracking system No tracking system
designed i.e. vector 1 contains the historical PV output data, vector Orientation & Tilt 110° & 3° (Lower/South Roof)
Orientation & Tilt 20° & 3° (Perimeter)
2 comprises the values of solar irradiance and module temperature
Orientation & Tilt 20° & 6° (Core)
in vector 3. The output forecast results highlights that, the predic- Module technology Polycrystalline silicon
tion error (NRMSE) is 12.57%, 12.60% and 10.91% with input vector Module size 1650  992 mm
1, 2 and 3 respectively. A another research study (Liu et al., 2015) Number of modules 1806
proposed that, a PV output forecast model with historical PV out- Number of inverters 32 (31  12.5 and 1  5000)

put data, weather data of current day, historical aerosol index

(AI), historical wind speed, weather and humidity data are as fore-
cast model input. Different case studies were designed for cloudy
and sunny day forecast with different set of inputs for the perfor-
mance analysis. The prediction results demonstrate that, forecast
error is 7.34% and 7.04% without AI and with AI as forecast input
respectively for sunny day forecast case study. The results demon-
strate that; the PV output forecast model performance varies with
change in input variables.
3. Solar output power profile
The University of Queensland (UQ), Australia install the PV
arrays at different location. These PV sites are UQ St. Lucia campus,
UQ Gatton campus, Heron Island and North Stradbroke Island with
installation capacity of 1.22 MW, 3.525 MW, 54 kW and 40 kW
respectively. UQ center is the largest PV array installed at UQ St.
Lucia campus as shown in Fig. 3.
The technical parameters details of PV UQ center is given in
Table 1. The characteristics of other UQ solar facility is given in
Table 2. Online solar data management system record reading of
every minute for different parameters. These recorded parameters
are PV output power, humidity, air temperature, wind speed and
direction.
3.1. UQ center array PV output profile
The PV output power pattern can be analyzed using minutely
recorded time series data of a full year 2014. The PV output data
series of year 2014 contains N = 525,600 values of different param-
eters. The recorded parameters of UQ center PV array are solar
output power, humidity, air temperature, wind speed and direction
at any time instant t as given in Eq. (2).
fpt ; t ¼ 1; 2; 3; . . . ; Ng ð2Þ
where N represents the number of data points. Fig. 4 depicts the
yearly PV output power profile of UQ center array. The months of
the year are on x axis and y axis denotes generated output power
in watts. A variation in generated PV power graphs can be observed
over different months of the year 2014. The generated output power
is higher in first four months of the year and lower in next months.
However, the generated output power remains at medium form
September to December 2014. There are number of factors affecting
the solar output power. It is mainly due to meteorological related
variables which are affecting the output.
The recorded 1 min data contains humidity, air temperature,
wind speed and direction for complete cycle of 24 h and have
1440 data samples. However, the solar data is available from
5 AM to 7 PM. The rest of solar data is not available in solar data
management system due to unavailability solar output. Therefore,
solar time series data contains 841 data points and rest of values
solar power output values considers zero in order to synchronize
the with meteorological data. Meteorological data contains the
1440 sample for 24 h of the day and 525,600 for full year.
A one day PV output profile of UQ center array is shown in
Fig. 5. The graph represents the 841 data samples of solar output
power from 5 AM to 7 PM. The data samples are not recorded by
PV data base management for rest of the day hours. It is due to
unavailability of solar output power for remaining hours of the
day. However, there might small amount of power generated by
PV array for rest day hours. But it is not significant PV output
130 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

Table 2
Characteristics of Selected UQ PV sites.

Sites Longitude Latitude Height above sea level (M) Module area (M2) Modules Inverters Nominal output (kWp)
0 00 0 00
GCI 153°00 52 E 27°29 51 S 27+ BH 941.2 575 9 138
LEB 153°290 4400 E 27°000 4900 S 43 612 374 7 89.76
CP1 153°000 3700 E 27°290 4200 S 23 2305 1412 26 338.9
CP2 153°000 3500 E 27°290 4200 S 23 2305 1412 26 338.9
UQC 153°000 54.800 E 27°290 4500 S 28 2956 1806 32 433.44
AEB 153°000 5300 E 27°290 5800 S 18 + BH 640 383 10 95.75
GSRFDA 152°200 14.100 E 27°330 41.500 S 88 5784 7200 – 684

UQ Centre (UQC), Sir Llew Edwards Building (LEB), Car Park 1 (CP1), Car Park 2 (CP2), Global Change Institute (GCI), Building, Advanced Engineering Building (AEB) and Gatton
Solar Research Facility Dual Axis (GSRFDA), BH = Building Height.

5
10

4.5 Solar Output Power

Higher PV Ouput Power
Medium PV Ouput Power
4
Lower PV Ouput Power
3.5

3
Power (W)

2.5

1.5

0.5

0
Jan. Feb. March April May June July Aug. Sep. Oct. Nov. Dec.

Yearly Solar Power Data Points

Fig. 6. Solar output power profile of year 2014.
Fig. 4. Yearly (2014) solar output plot of minute data.

Fig. 7. The per unit curves of PV output power and air temperature.

Fig. 6 represents the UQ center array solar profile of year 2014.

Fig. 5. Solar PV output profile of the day 01-01-2014.
In this graph number of days on X axis, data points of on the Y axis
and magnitude of power on Z axis. As discussed earlier the solar
power to use. It is observed that, the value of PV output power output data is from 5 AM to 7 PM is available and it can be
increases significantly as time increases. Graphs shows that, the observed for PV output pattern of UQ center array is similar to
value of PV output varies from 5 am to 7 am. However, with yearly plot in 2D. The PV output power varies thought the year
increasing PV output power, large fluctuations can be observed 2014. Similar output pattern can observe from 3D PV output
from 7 am to 11 am due meteorological factors. The PV output profile.
power was increased with passage of day time. It reaches to max- Fig. 7 highlights the relative change in PV output power with air
imum level during the middle of the day. The PV output power temperature. It can be observed that, the PV output power varies
start decreasing after 2 pm due decrease in temperature. with change in air temperature.
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
The amount of generated power is increased with raise in air
temperature and vice versa. This indicates the correlation between
PV output power and air temperature. Some other research studies
also reported that, there is strong correlation between temperature
and PV output power (Chen et al., 2011). Therefore, Air tempera-
ture can be applied as forecast model input in order to predict
the PV output correctly.
Fig. 8 depicts the variations in PV output power with change in
wind speed, which is recorded data in solar data management sys-
tem. The wind speed plays a role in heat dissipation and as result it
leads to reduction in PV cell temperature. Therefore, PV output
power will be reduced with lower the cell temperature. Fig. 8 indi-
cates, the PV output power pattern does not follow the exactly the
wind speed pattern. In day, the PV output power is at higher level
as compare the wind speed. After that, the per unit PV output
power was reduced with increase in wind speed. However, similar
PV output power pattern with wind speed was not observed for
reset of year. Therefore, relatively a weak correlation is observed
between PV output power and wind speed in comparison of
temperature.
Figs. 9–11 show the relationship between PV output power and
solar irradiance during clear day (CD), partially cloudy (PCLD) and
cloudy day (CLD), which are selected from year 2014. It can be
observed that in clear day graph, the PV output power fairly follow
the solar irradiance curve. It can be observed that, solar irradiance
fluctuates with high ramp rate. As a results, similar pattern is
observed for PV output power profile. A similar trend is observed
Fig. 8. The per unit curves of PV output power and wind speed.
Fig. 9. Relationship between PV output and solar radiation for clear day.
131
during the partially cloudy day as shown in Fig. 9. The solar irradi-
ance is less than the 400 W/m2 during the major portion of day
time except to hour 10–13. The solar irradiance goes up to
1250 W/m2 during the hour 10–13 and PV output power also fol-
low the same pattern. The sharp changes in PV output power is
observed during the hour 10–13 and solar irradiance pattern is fol-
lowed by the PV output power, which indicates the strong positive
correlation among them. It can be observed from Fig. 11 that, the
solar irradiance peak goes up to maximum 400 W/m2 in cloudy
day, which is less half of clear day. Therefore, average solar PV out-
put power is quite lower than the clear and cloudy day. In addition,
higher level fluctuations in solar irradiance are observed during the
cloudy day than the clear and partially cloudy day. As a result, solar
PV output power is also variable throughout the day.
It can be concluded that from the above figures, PV output
power have very strong correlation with solar irradiation as com-
pared to air temperature and wind speed. Therefore, these influen-
tial variables are recommended as forecast model to accurately
forecast the PV output power in variable meteorological condition.
In addition, these variables add more uncertainty in PV output
power, which may create some critical issue directly or indirectly
in PV integrated power grid.
Some other meteorological related parameters are also affected
the PV output power such as air sole index, cloud cover, shading,
humidity and wind speed. The forecast accuracy PV output forecast
model may be enhanced using large number of inputs. However,
forecast model computational cost and complexity will be also
Fig. 10. Relationship between PV output and solar radiation for partially cloudy
day.
Fig. 11. Relationship between PV power and solar radiation for cloudy day.
132 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
increased due to aggregating the large number of input parame-
ters. Therefore, it is utmost important to design a forecast model
with optimal number of forecast model inputs to deal with com-
plexity issue.
4. Classification of forecast techniques
Solar forecasting methods can be classify into different cate-
gories named as persistence method, physical techniques, statisti-
cal techniques, hybrid models and some forecast methods as
shown in Fig. 12 (Soman et al., 2010). Majority of forecast tech-
niques utilized the historical meteorological data and other exoge-
nous variables as forecast model input (Pelland et al., 2013). There
is some other solar irradiance and PV output forecast, which use
satellite imaging for data acquisition (Rezk et al., 2015). These
methods are not listed in following below classification.
4.1. Persistence forecast
Persistence forecast model is useful tool to analyze the perfor-
mance of other prediction model as reference model. The main
objective of designing a complex forecast model is to achieve the
better forecast accuracy than the subsequent prediction models
with less computational cost. However, persistence model is com-
mon reference method with less computational cost and to com-
pare with other short term solar output power forecast models.
The value of PV output power at time t + 1 is highly correlated to
the value at t. The future value PV output power can be predicted
output power at t. Similarly, persistence model can also be applied
to other forecast applications.
The persistence model can be utilized as benchmark for differ-
ent forecast models. The forecast accuracy of persistence based
model is largely affected due to change in forecast horizon. It is
also varies with change in meteorological condition such as tem-
perature, irradiance, wind speed and humidity level. Therefore,
Persistence/ Physical
Naive method Approach
Numeric Arficial
Weather Neural
Predicon network
HIRM
MM5 GFS FNN BPNN
LAM
Fig. 12. Classification of forecast techniques.
persistence based forecast model shows higher forecast error and
it is used to compare with proposed in order to analyze the perfor-
mance. In Perez et al. (2010) research study, authors proposed
forecast model is evaluated with comparison of persistence model
results.
4.2. Physical models
The popular physical model is numeric weather predictor
(NWP). This predictor is based on mathematical set of equations,
which describe physical state and dynamic motion of the atmo-
sphere. These models are based on the PV plant characteristic such
as location, orientation historical data, and meteorological vari-
ables. It is also relay on the different forecasted weather variables
such as PV system characteristics, global horizontal irradiance
(GHI), global horizontal irradiance (GHI), relative humidity, wind
speed and direction along with PV models (Lorenz et al., 2011;
Mathiesen and Kleissl, 2011; Pelland et al., 2013). The forecast per-
formance of physical model is higher, when the weather conditions
are stable (Soman et al., 2010). However, the forecast accuracy is
largely affected due to sharp changes in meteorological variables.
4.3. Statistical techniques
Statistical techniques are based on the learning process of the
forecast model with historical influential variables. The forecast
model tries to reduce the network learning error by using the dif-
ference between network predicted PV output power and actual
measured values. Therefore, statistical models are based on histor-
ical patterns. Therefore, forecast accuracy of statistical model is
depend on the length and quality of historical input data. Statistical
techniques can be further segregated into two sub groups named
as time series and artificial intelligence (AI) based forecast models.
The time series forecast models are multiple linear regressions,
support vector machines (SVM), autoregressive moving average
(ARMA), autoregressive integrated moving average (ARIMA) for
Forecast
Techniques
Stascal Hybrid
New Techniques
Approaches Structures
Time Series
RBF ARX ARIMA ARMA
NWP NN+
ANFIS
Ens. Fuzzy WT +NN T.S
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
non-stationary time-series and autoregressive (integrated) moving
average with exogenous inputs (ARIMAX), etc. (Mohamed and
Bodger, 2004; Bacher et al., 2009; Alfares and Nazeeruddin,
2002). The different tine series for forecast models are discussed
below.
4.4. Linear models or time series models
It is observed that the, time series forecasting has been applied
for different applications with higher degree of success since the
last decade. In statistical techniques, variables are used as model
input having correlation with output and predictors. Several stud-
ies has been published for time series modeling (Rodriguez, 2010).
In this research study, the comparison of time series techniques is
presented. In Kasten and Young (1989), AR model is used to inves-
tigate the forecasting performance of PV power with other predic-
tion techniques.
4.4.1. ARMA model
ARMA model is combination of two basic models which are
autoregressive (AR) and moving average (MA) model as given in
Eq. (3).
X
p X
q
XðtÞ ¼ ai Xðt  1Þ þ bYðt  jÞ ð3Þ
i¼1 j¼1
Eq. (3) represents the forecasted PV output as it is represented
in form of function XðtÞ. P represent the number of AR process in
the model and ai is ith AR coefficient of the forecasting model.
Where second part of the equation eðtÞ represents the jth coefficient
of MA model. Y(t) represents the white noise and it is not corre-
lated forecast model output variable (Hamilton, 1994). Auto cor-
rected time series data can be treated by Autoregressive Moving
Average (ARMA) model. ARMA is considered as good prediction
model to forecast the future values of provided time series with
stable input variables. ARMA model refer as (p, q), where p repre-
sent the order of AR model and q denotes the order of MA model.
The ability to extract the statistical properties and Box Jenkins
adoption are the main reasons to the popularity of ARMA model
(Boland, 2008). In addition, several types of time series can be
characterized by using ARMA model with set of equations of differ-
ent order. The ARMA model more suitable for stationary time ser-
ies data (Hansen, 1995).
4.4.2. ARIMA techniques
Auto-Regressive Integrated Moving Average (ARIMA) time ser-
ies model an extension to ARMA model. It is widely used for differ-
ent modeling and forecasting application with acceptable level of
forecast accuracy (Box et al., 2011). ARIMA for (p, q) for the time
ðX 1 X 2 ; X 3 ; . . .Þ can be defined as given in Eqs. (4)–(6).
Up ðZÞDd X t ¼ UðZÞat ð4Þ
Up ðZÞ ¼ 1  /1 Z  /2 Z 2      /p Z p ð5Þ
Hq ðZÞ ¼ 1  h1 Z  h2 Z 2      hp Z q ð6Þ
where Z is backward shift operator. Therefore, back difference oper-
ators are ZX y ¼ ZX y1 , D ¼ 1  Z. Up and Hq are the polynomials of
degree p and q. As mention earlier, ARIMA is product of AR model,
integrating part I and MA model. Therefore, ARIMA (p, q, q) model is
the combination of AR (p), integrating part IðdÞ ¼ Dd and moving
average MA (q). In order to avoid the unbounded process, the poly-
nomials parameters such as U and H are chosen in such a way that,
the both polynomials lies outside the unit circle. The variation from
the fixed distribution with zero mean and variance ra is called
133
white noise. Some of the inherent features of time series can be
extracted by using backshift operator and white noise process.
The backshift operator and the white noise process describe the
intrinsic features of the time series. In addition, the adjacent obser-
vations are dependent to independent time step t of the white
noise process. In Hansen (1995), describes the working of ARIMA
(Auto-Regressive Integrated Moving Average) methods can used
as reference in prediction models domain. In research study
(Reikard, 2009), ARIMA model is used to predict the solar irradi-
ance and forecast results are compared ANN based forecast model.
The results highlights that, the ARIMA based forecast model trace
the Sharpe changes of solar irradiance pattern and produces higher
forecast accuracy than the benchmark techniques. There is poten-
tial to apply the ARIMA model stand along or hybridize with other
models for PV output power forecast.
4.4.3. CARDS model
Autoregressive (AR) and dynamical system (DS) models are
coupled together. It is used to predict to time series data called
CARDS model. This model is also used to forecast the time series
solar irradiance (Huang et al., 2013). The dynamical system equa-
tion can be derived using Lucheroni model as given in Eqs. (7)
and (8).
R_ ¼ x ð7Þ
ex_ ¼ kðx þ RÞ  kð3R2 x þ R3 Þ  ex  cR  b  f ð8Þ
where f is noise term and k; k; c; e; b are tunable parameters. In
above equation R_ represents the derivative of R with respect to time.
Where x denotes the double derivative of R w.r.t. time as given in
Eqs. (9) and (10).
Rtþ1 ¼ Rt þ X t Dt þ xt ð9Þ
h   i
X tþ1 ¼ X t þ kðX t þ Rt Þ  k 3R2t X t þ R3t  eX t  cRt  b
Dt
 þ at ð10Þ
e
where Dt represents the time step change and by using ordinary
least square method other parameter can be determined such as
k; k; e; c; b. In Boland (1995), authors utilized the Fourier series tech-
niques to de-seasoned the time series data. It is due to partial
inability of autoregressive process that it cannot model it alone.
Therefore, Fourier series is subtracted to from original series in
order to get the residual series. However, at the peak reversion,
the AR model is efficient enough to capture the series peaks. In
Lucheroni (2009), first who apply resonating model on power sector
application. Therefore, a good level of fitting is achieved for residual
series by using curvature’s proxy. The CARDS model shows good
results in comparison evaluated techniques in Kostylev and
Pavlovski (2011). The results of this study highlights that, CARDS
model produce RMSE 16.5% as compared to other implemented
model with RMSE 17% in clear day and 32% in cloudy at 1 h time
step.
Number of time series techniques are applied to different fore-
casting application along with different model inputs and forecast
horizons. There is potential to utilize the other time series tech-
niques for PV output power forecast such as stochastic time series
(Chakhchoukh et al., 2011), autoregressive moving average (Chen
et al., 1995), linear regression (Amral et al., 2007), general expo-
nential technique (Christiaanse, 1971; Marín and Sandoval,
1997). Generally, statistical techniques provide higher forecast
accuracy. Majority of time techniques provides the higher forecast
accuracy, if the forecast model input pattern is smooth. However,
sharp or abrupt changes in meteorological variables such as
134 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
temperature, irradiance, wind speed and humidity leads to
increase in forecast error.
4.5. Artificial intelligence techniques
Artificial intelligence (AI) based techniques popular among the
researcher since three decades for forecast applications. Among
the AI techniques, neural network (NN) is more poplar and used
as power computational tool for different predication applications
with higher degree of success since 1980. Generally, NN models
produces higher forecast accuracy. It is due to its ability to capture
the sharp changes in the output with help of intelligent training
process of the network. An adaptive and robust NN training meth-
ods can further improve the capability of the network to learn the
complex relationship between input and output variable
(Patterson, 1998).
A number of learning techniques are designed to train the NN
effectively such gradient and population based techniques. NN
model tries to predict the future output pattern using the different
set of input data. The forecast accuracy of the model is calculated
with real time data and predicted values. The forecast accuracy
of model can be further enhanced by carefully selecting the differ-
ent influential parameters. These parameters are the normalized
and suitable number of forecast model inputs, appropriate training
algorithm, optimized network structure, appropriate learning algo-
rithm, suitable training data and optimized network structure may
increase the overall performance of network and reduce the com-
plexity (Ho et al., 1992). The primary steps ANN based load forecast
model are provided in Fig. 13.
Input selection of PV output forecast model is one of most crit-
ical part in the design process. The forecast accuracy varies with
change in type and number of model inputs. It is due to large
dependence of PV output power on meteorological variables. Sec-
ondly, the real time meteorological and PV output recorded data
is used to train the forecast model and compare the model perfor-
mance. This data may contains several missing data points, sharp
peaks and variations. Therefore, input preprocessing technique is
need to be apply on data for smoothing before applying the data
as forecast model input. After that, the historical PV output power
data is divided in two groups named as training and testing data.
The training data of forecast model is used for learning of the net-
work to forecast the future values. Testing data is used to analyze
the performance of forecast model by comparing the actual and
predicted values. After that, neural network is initialized with dif-
Selection Of Forecast Model Inputs
Pre-processing of Input Data for
Forecast Models
Split Data Into Testing And Training
Sets
Initialize and Train ANN Model
Post-processing of Output Data
Calculate And Compare Forecast Error
Of Different Models
Fig. 13. Neural network based forecast model steps.
ferent layers based on the type and complexity of the problem. The
network is trained using training data, which is applied as forecast
model inputs. A post processing techniques can be used before cal-
culating and analyzing the performance of prediction model.
4.6. Significance of ANN approach
Artificial Neural network based model has better capability to
map the input as model output without formulating the complex
relationship between input and output (Fausett, 2006). McCulloh
and Pitts conduct a research to model the nets based bio-system
for simple logical operation in 1942 (McCulloch and Pitts, 1943).
They attempt to model the simplest form of nonlinear model of a
neurons. This research come up with new world of computational
calculations. ANN models are robust in nature due to dynamically
respond to rapid changes with help of interconnected neurons and
learning methods. Several neural network learning techniques of
NN are available with different computational complexity and con-
vergence rate for global optimum solution. The computational
complexity of the network, convergence rate and training time
can be reduced by optimizing the different parameters (Shekhar
and Amin, 1992). These parameters are correlated forecast model
inputs, preprocessed training data of the network, optimal NN
structure and robust NN training techniques, etc. ANN based mod-
els have been implemented on several fields of life such as aero-
space, Bio-medical, research and development of socio economic
applications, automotive industry, electronics industry, stock mar-
ket and finance industry (Lai, 1998).
4.6.1. Artificial neural network
In the last decade, ANN models are utilized as power full tool for
different real life and computational applications. ANN have ability
to draw complex relationship between input and output using
learning mechanism of the network. Through learning algorithm
of neural network, ANN model can map the complex input output
relationship by using feedback error system. ANN based models
are robust and adaptive in nature and performed well up to certain
level even under the noisy environment. The summary of early
stages developments of ANN model are given below in Table 3.
4.6.2. Artificial neural network architecture
The artificial neural network (ANN) is network of connected
artificial neurons in different layers such as input, hidden and out-
put layers. The basic artificial neural network as shown in Fig. 14.
The neurons are connected in different layers with synaptic
weights values. The learning algorithm of neural network tries to
map the input and output relationship by updating the synaptic
weights values. The network generated output is compared with
desired output and then error is calculated. Therefore, the weights
and biases values of NN are updated based on the error. The acti-
vation function is applied to weighted input for output of the
network.
This cycle will continue until the desired output achieved.
The weighted sum of inputs can express in the form mathemat-
ical relationship as given below:
!
X
n
Ai ¼ g W ij  ai ð11Þ
i¼0
where Ai ; W ij and aj are network output, connection weight of Ith
neuron to Jth layer neuron and network input respectively. A neural
network may have multiple inputs and single output. There are two
basic operation of neural network such as training and testing. At
training stage network is trained using learning the algorithm to
learn the basic relationship between input and output. The network
output is compared with desired output at testing stage. The output
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 135

Table 3
Summary of major ANN developments.

Number Year Authors References ANN developments

1 1942 McCulloch & Pitts McCulloch and Pitts (1943) Proposed the concept of first artificial neurons
2 1946 Hebb & Pitts Morris (1999) Proposed first learning algorithm to memorize the adapting weight values
3 1958 Rosenblatt Rosenblatt (1962) Developed a first form of artificial network with Perceptron
4 1959 Lee Nilsson (1965) Proposed the Artron
5 1960 Widrow and Hoff Widrow and Hoff (1960) Proposed LMS training method and Adaline (Adaptive Linear Neuron)
6 1982 Hopfield Hopfield (1982) Design Hopfield neural network
7 1988 Widrow and Winter Widrow and Winter (1988) Design a network using Adeline neurons which is called Madaline
8 1988 Rumelhart et al. Widrow and Winter (1988) Proposed multilayer perceptron base neural network with backpropagation algorithm
9 1987 Hecht-Nielsen Hecht-Nielsen (1987) Proposed the concept of self-organizing mapping using counter propagation network
10 1988 Chua & Yang Chua and Yang (1988) Design cellular neural network

Fig. 14. Basic ANN architecture (Khotanzad et al., 2002).

of the network varies with change in activation function, architec-
ture and inputs of neural network. Different types of activation
functions are discussed in next section.
4.6.3. Activation function
The output of the network is generated by using activation
function by summing of weighted inputs. Therefore, activation
function of network acts as squeezing function to transfer the input
in the form of output. Different activation functions are available
for neural network and output of the network also varies with
change of activation function (Zhang et al., 2007). There are num-
ber of transfer functions are available such as Gaussian radial basis,
1998). The first and second layer of the network can be differenti-
ate on the basis of synaptic weights. The first layer synaptic
weights can be determined by using input data set. The weight val-
ues of input layer are fixed at first stage and the second layer
weights are determined. The RBFNN network is trained using
unsupervised learning method as only input data is provided to
the network. The supervised learning method is utilized for second
layer weights determination. Classic least mean squares is used for
optimization. The basic form RBFNN mapping is given in Eq. (11).
The RBFNN architecture is shown in Fig. 16.
X
M

uni and bipolar polar step function, linear function and sigmoid
function respectively. Table 4 summaries the different types of
activation function along with derivative and diagrams. There are
hard and fast rules for transfer function selection. The activation
function of neural network can be selected based on nature of
application (Mellit and Kalogirou, 2008).
4.6.4. Multi layer perceptrons neural network
A number of complex problems from different research
domains, which cannot be solved by using single layer neural net-
work. It is due to complex input and output relationship between
different variables. Multilayer perceptron’s neural network
(MLPNN) have the ability to map the input output relationship
using proper training of network. There are one or more than hid-
den layers between input and output layer of the network. These
layers are connected with each other. The multilayer perceptrons
neural network (MLPNN) was for different forecast applications
such as load and electricity price forecasting (STLF) (Tasre et al.,
2011; Raza et al., 2014). A typical MLPNN architecture for PV fore-
cast is represent in Fig. 15.
4.6.5. Radial basis function network (RBFNN)
The radial basis function neural network (RBFNN) is considered
as two-layer neural network. The learning process of RBFNN can be
divided in two different stages (Madan et al., 2003; Jain and Martin,
Y k ðxÞ ¼ W kj /j ðxÞ þ W ko ð12Þ
j¼1
4.6.6. Recurrent neural network
Recurrent neural network (RNN) demonstrate the higher capa-
bility to learn different complex relationships and computational
structures. A real-time recurrent learning network (RTRL) contains
input layers, processing layers (feed forward and connections lay-
ers) and some additional node elements. The successful application
of RNN model is discussed comprehensively in Hertz et al. (1991).
In Elman (1990), authors proposed RNN architecture with feedback
back loop. It is taken from hidden layer of the network to input
layer. However, another research studies the proposed the feed-
back from output layer to input layer of the network (Jordan,
1997). These feedback loops are used to minimize the network
learning error using training process.
In fully connected recurrent neural network (RNN) every pro-
cessing node is connected with other processing node and with
itself as well. Therefore, the output of RNN at any time is depends
on the two parameters, which are feedback signal at previous time
step and input signals. In Williams and Zipser (1989), authors ana-
lyze and perform experiments on the learning of real time of RNN.
The network was trained in every processing cycle. The activation
function of the network is weighted sum of feedback and current
input signals. Therefore, the activation function is given in Eq. (13).
136 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

Table 4
Artificial neural network transfer functions.

Class Function Derivative Diagram

 
Unipolar step function 1 if ; x > 0 1 if ; x – 0
f ðxÞ ¼ HðxÞ ¼ dðxÞ ¼
0 if ; x < 0 1 if ; x ¼ 0


Bipolar step function f ðxÞ ¼ sinðxÞ ¼ 2HðxÞ  1 1 if ; x – 0
dðxÞ ¼
1 if ; x ¼ 0

8
Unipolar linear function <0 if x < 1 dðxÞ ¼ 1=2½Hðx þ 1Þ  Hðx  1Þ
f ðxÞ ¼ HðxÞ ¼ 1=2ðx þ 1Þ if jxj < 1
:
1 if x > 1

8
Bipolar linear function <1 if x < 1 dðxÞ ¼ ½Hðx þ 1Þ  Hðx  1Þ
f ðxÞ ¼ HðxÞ ¼ y if jxj < 1
:
1 if x > 1

Unipolar sigmoid function f ðxÞ ¼ ð1=1 þ ex Þ dðxÞ ¼ f ðxÞð1 þ f ðxÞÞ

Bipolar sigmoid(hyperbolic tangent) f ðxÞ ¼ tanhðxÞ dðxÞ ¼ ð1 þ jf ðxÞ2 jÞ

 
Gaussian radial basis f ðxÞ ¼ exp kx  mk2 =r2 2ðx  mÞf ðxÞ=r2

X
pþ1 X
q 4.6.7. Feed forward neural network
Sk ðtÞ ¼ ðW ik X p ðtÞÞ ðV kq Y q ðtÞÞ ð13Þ Feed forward neural network (FFNN) is relatively less complex
p¼1 q¼1
NN architecture. In FNN, the information moves from input to out-
put layer in forward direction. Network can be single layer or
where Sk ðtÞ is activation function at the time of processing node k
multi-layer but information moves only on one direction. There
and V kq is the connection weight of the node q which is connected
is no feedback loop or cycle for information to process. In feed for-
with node k. W pþ1 is the value of the bias. The output of node k is
ward neural network, the information reach at output layer
given below in Eq. (14).
through input and hidden layer of the network. Fig. 18 highlight
Y k ðt ¼ 1Þ ¼ f k ðSk ðtÞÞ ð14Þ the neural network having input, hidden and output layer with 3,
2, 3 neurons respectively. Feed forward neural network was also
where f is sigmoid activation function. The Recurrent neural net- applied for several forecasting and pattern recognition application
work (RNN) architecture is shown in Fig. 17. (Ahmad et al., 2009; Malki et al., 2004).
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 137

Neural Network
Historical PV 11 Architecture
Output Data

Temperature 2 1

PV
Forecast
Humidity 3 2 1

Wind Speed 4 20

Cloud Cover 38
8

Input Hidden Output

Layer Layer Layer

Fig. 15. Multilayer perceptron neural network.

Fig. 18. Feed forward NN structure.

Fig. 16. Radial basis function network (RBFNN) architecture (Rivas et al., 2004).

Fig. 19. Feed back NN structure.

problem (Hahn et al., 2009). A feedback neural network having 3

Fig. 17. Recurrent neural network (RNN) architecture (Smith and Jin, 2014).
4.6.8. Feedback neural network
Feedback neural network allows the information to move one
layer to previous layer by using feedback system. The output of
network influences the input as the output information feed into
the network. The feedback information is the error function, which
can be calculated by using desire and network output. The network
tries to achieve the desire level by back propagating the network
error. Feedback neural network is dynamic in nature as the error
function feedback to network and network tries to achieve the
equilibrium state. It is reported that, feedback neural network is
suitable for dynamic, complex and time lagged pattern recognition
input, 2 hidden and 3 output layers neurons shows in Fig. 19.
The systematic and comprehensive literature review of
reported solar PV output power and irradiance techniques are pro-
vided in three tables. Majority of the forecast techniques have
potential to apply on other predictions problems. However, fore-
cast accuracy may vary due to different performance affecting
parameters. The forecast literature is segregated based on the fore-
cast horizon. The twenty-four hours or one day ahead forecast
methods are provided in Table 5. Tables 6 and 7 describe the fore-
casting techniques for 1 min to less one day ahead and more than
one day ahead forecast respectively. This table provides the author
details, year of publication, and name of the country (where PV
plant is installed and real time PV output data used as model
inputs). In addition, it also provides the forecast horizon, forecast
error, forecast method and benchmark techniques. Several data
basis have been studied for literature such Elsevier, IEEE, Hindawi,
Taylor & Francis and Springer using different search engines.
4.7. ANN and classical time series models comparison
In Reikard (2009) and Sfetsos and Coonick (2000), the compar-
ison of artificial neural network and time series is investigated
under different scenarios. Both research studies suggest that, the
error of advance regression model is reduced by the factor of
0.6–0.8 to comparison of simple regression techniques. In
 138
Table 5
A review of one day ahead solar and PV output power forecasting techniques.

Ref. Year Country of Journal/conference Forecast horizon Forecast error Forecast model Comments
PV data set
Chen et al. (2011) 2011 China Solar Energy 24 h ahead MAPE < 9.28% Self-organizing map (SOM) The performance of different test case studies on sunny, cloudy day and
trained ANN model rainy day. However, forecast model performance varies with day type
Ding et al. (2011) 2011 Ashland, Procedia 24 Hours ahead MAPE 10.06% Artificial Neural Network (ANN) Backpropagation learning algorithm based ANN is used to forecast the 24 h
USA Environmental PV output
Sciences
Cococcioni et al. 2011 Italy IEEE conference 24 h ahead MAPE 5% Artificial neural networks (ANN) Time-series analysis model NARX with feedforward neural network is used
(2011) to predict 24 h PV output with varying number of hidden layer, number of
neurons and training window
Kang et al. (2011) 2011 Korea IEEE conference 24 h ahead Approximately k-means clustering method K means clustering technique is used at first stage and five years historical
MAPE 11% data was analyzed to classify them based on cloudiness
Mori and Takahashi 2012 Japan IEEE conference 24 h ahead Error 0.228 pu Generalized Radial Basis Generalized Radial Basis Function Network (GRBFN), Deterministic
(2012) [error is Function Network (GRBFN) Annealing (DA), and Evolutionary Particle Swarm Optimization (EPSO)
quantized in based Neural Netwrok
standard method]

M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

Haque et al. (2013) 2013 USA IEEE conference Seasonal one day MAPE 12.11% Wavelet transform (WT) and Wavelet transform (WT) is used to remove the unexpected spiks and sharp
ahead fuzzy ARTMAP (FA) changes in input data. Furthermore, fuzzy ARTMAP (FA) was employed to
forecast the PV output
De Giorgi et al. 2014 Italy IET Journal 1–24 h ahead NAME 6.50% Multi regression analysis and the Multiple regression analysis have be employed and Elman artificial neural
(2014) Elmann artificial neural network network (ANN) model is used to predict the load demand
(ANN)
Sansa et al. (2014) 2014 Barcelona, IEEE conference 24 h ahead Error 0.027 pu Artificial Neural Networks (ANN) Nonlinear Auto Regressive models with neural network was used. However,
Spain the forecast model performance varies over the different forecast horizons
B.M. Shah et al. 2014 China Signal Processing 24 h ahead 9.13–9.30 BP (Back Propagation) neural A combination of particle swarm optimization and Back Propagation based
(2015) for network (NN) neural network was used to predict the PV output
Communications
Yang et al. (2014) 2014 Taiwan IEEE Transactions 24 h ahead MRE 3.295% Self-organizing map (SOM) and Self-organizing map (SOM) and learning vector quantization (LVQ)
On Sustainable learning vector quantization techniques used for classification of historical data and support vector
Energy (LVQ) regression (SVR) was used for train Fuzzy inference system
Tao and Chen (2014) 2014 China IEEE conference 24 h ahead Error 8% Genetic Algorithm based neural The proposed Genetic Algorithm (GA) based PV forecast model results
network compared with back propagation NN based forecast model
Junior et al. (2014) 2014 Hokkaido, Energy Procedia 24 h ahead Minimum RMSE Principal Component Analysis Principal Component Analysis (PCS) technique gives lower forecast error
Japan 2.4% than without PCA model
Ramsami and Oree 2015 USA Energy Conversion 24 h ahead RMSE 2.74% Generalized regression neural Stepwise regression model use to select the input and hybrid model of
(2015) and Management network, feedforward Neural Generalized regression neural network, feedforward neural network and
network and multiple linear multiple linear regression
regression
Liu et al. (2015) 2015 China IEEE Transactions 24 h ahead MAPE 7.65% Back propagation (BP) based Aerosol index (AI) was used along seasonal classification and back
On Sustainable ANN model propagation (BP) based ANN model for cloudy day forecast
Energy
Leva et al. 2015 Italy Mathematics and 24 Hours ahead NAME 11% Artificial Neural Network (ANN) ANN based model is applied to analyze the performance during sunny,
Computers in partially cloudy and cloudy day
Simulation
Zhang et al. (2015) 2015 USA Solar Energy 1 h and 1 day Minimum RMSE Ramp forecasting method Uniform forecasting method without ramp, ramp forecast and ramp
ahead 0.995% forecasting threshold changes
B.M. Shah et al. 2015 Japan IEEE Transactions 24 h ahead RMSE 2.74% Grid Point Value (GPV) Grid Point Value (GPV) was employed to forecast the cloudy/rainy/snowy
(2015) On Sustainable days
Energy
Dolara et al. (2015) 2015 Italy Solar Energy 24 h NAME and WAME Physical model There Physical models are designed for desi monocrystalline and
between 0.5% and polycrystalline PV panels
10%
Table 6
A review of one minute to day ahead solar and PV output power forecasting techniques.

Ref. Year Country of Journal/conference Forecast horizon Forecast error Forecast model Comments
PV data set
Chupong and Plangklang 2011 Thailand Energy Procedia 11 h MAPE 16.83% Elman neural network The proposed Elman neural network based forecast model
(2011) than Recurrent Neural Network based model
Pedro and Coimbra (2012) 2012 California, Solar Energy 1 and 2 h-ahead 35.1% Auto-Regressive Integrated Moving GA optimized Artificial Neural Networks (ANNs) outperform
USA Improvement in Average (ARIMA), and ANN Genetic than the other forecast models
forecast results Algorithm (GAs/ANN)
Mandal et al. (2012) 2012 USA Procedia 1 h ahead MAPE from Wavelet transform (WT) and artificial Radial basis function neural network (EBFNN) forecast model
Computer Science 2.38% to 4.08% intelligence (AI) is used with wavelet transform was tested for spring,
summer, winter and autumn’s sunny and cloudy day
Lonij et al. (2013) 2013 USA Solar Energy 30–90 min RMSE Persistence model Forecast results show that, the prediction performance
improvement increased by numerical weather Model
23%
Marquez and Coimbra 2013 USA Solar Energy 30, 60, 90, 120 min RMSE < 2.95% Artificial neural network (ANN) ANN model inputs are satellite image analysis including
(2013) velocimetry and cloud indexing to enhance the forecast
accuracy

M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

Kaur et al. (2013) 2013 USA Energy Conversion 15 min and 1 h Error 9% and 3%s Persistence, machine learning and Forecast results show that, the auto regression is best suited
and Management regression-based forecasting models model for 1 h ahead forecast. Furthermore, the forecast
accuracy decreases with decrement forecast horizon from 1 h
to 15 min
Tuyishimire et al. (2013) 2013 USA IEEE conference 15 min to 12 h Not available Kalman Predictor Two methods was designed to forecast the PV generation
ahead
Yona et al. (2013) 2013 Japan IEEE Transactions 1 h ahead Max. RMSE Fuzzy theory and Neural Network Fuzzy theory was used for insulation and better training of
On Sustainable 1.68% neural network
Energy
Yang et al. (2014) 2014 Taiwan IEEE transactions 1 day ahead MRE 3.295% Self-organizing map (SOM) and learning Self-organizing map (SOM) and learning vector quantization
on sustainable vector quantization (LVQ) (LVQ) techniques used for classification of historical data and
energy support vector regression (SVR) was used for train Fuzzy
inference system
Gohari et al. (2014) 2014 San Diego, Energy Procedia 10 min and more 0.70 and 0.82 San Diego Sky Imager (USI) San Diego Sky Imager (USI) compared with Total Sky Imager
USA than 10 min (TSI) based forecast model and USI model demonstrate better
results
Yang et al. (2015) 2015 USA IEEE transactions 1–2 h ahead Min MAE 145.6 Spatial and temporal correlations Proposed spatial and temporal Correlation model along BPNN
on sustainable for 2 h ahead is used to forecast the PV output and compare with
energy forecast persistence model
Almeida et al. (2015) 2015 Northern Solar Energy Up to 15 min MBE < 1.3% Non-parametric model Non-Parametric forecast model use Numerical Weather
Spain Prediction (NWP) model and spatial and temporal as input
(latitude
42.2)
Zagouras et al. (2015) 2015 California, Renewable Energy 1 h and 3 h hours MAPE 8.458– Linear models, Artificial Neural Global optimization based linear model outperform than the
USA ahead 40.419% Networks, Support Vector Regression other benchmark models
Chu et al. (2015) 2015 USA Solar Energy 5, 10 and 15 min Minimum MAE Artificial neural network (ANN) with GA Genetic algorithm optimized ANN outperform than the other
ahead 21.02% optimization 3 models
Mori and Takahashi 2015 Évora, Electrical Power 6 Hours ahead MAPE 8–12% Vector auto regression framework Adoption of multivariate (spatial–temporal) model with
(2012) Portugal and Energy vector auto regression framework enhance the forecasting
Systems accuracy. However, the forecast accuracy may increase by
using better data mining and optimization techniques
Lipperheide et al. (2015) 2015 USA Solar Energy Few Minutes RMSE 3.2% Endogenous method Proposed model shows better forecast results than
Persistence and ramp persistence including other benchmark
models

139
140 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

Reikard (2009), the comparison of different models are provided

Historical power and weather data is applied to support vector machines (SVM) model
forecast models. However, the forecast accuracy of both model are close to each other
such as UCMA model, ARIMA, UCM model, a transfer function

ANN based model provides lower forecast error by using pre-processing techniques

Solar irradiance, Air temperature, cloud, humidity and sun position is used for both
model, hybrid model and neural network based model. The perfor-
mance comparison analysis highlights that, ARIMA model gives
better results over the 60, 30 and 15 min window. However, other

to predict the PV output power for sunny, foggy, rainy and cloudy day
studies reports that neural network based model outperform than
other comparative models (Mueller et al., 2004). It is reported that,
there is potential to improve forecast accuracy using robust fore-
cast techniques as PV (Reikard, 2009). It can be conclude that from
time series forecast techniques, it provides higher forecast accu-
racy under relatively smooth meteorological conditions. However,
the forecast error is increased under uncertain and sharp meteoro-
logical changes. NN models also not fully generalize over input
data of model inputs. Therefore, there is potential to apply the
hybrid techniques for PV output power forecast for precise
forecast.

4.8. Hybrid models for PV output forecast

Hybrid models are designed with the combination of two or

more techniques having superior attributes. It is reported that,
the hybridization of two or more techniques show better results
than the stand alone technique for forecasting problem. One of
Comments

main motivation of hybrid system is to explore the possibilities

of different algorithm combinations in order to enhance the fore-
cast accuracy. Hybrid models can produce better forecast results
by taking the advantage of each technique. Hybrid models were
used for several forecasting applications in order to achieve the
Weather classification and
support vector machines
Artificial neural network

higher forecast accuracy. Another motivation hybrid system of

Neural Network and

reduce the computational complexity and time for online forecast-

statistical method

ing application. Therefore, forecast output can be used for real time
Forecast model

energy management and other applications.

Some of the research studies have been reported that, the
hybrid models are effective for different forecast application such
(ANN)

(SVM)

as global horizontal irradiance, solar irradiance and electrical load

forecasting. In Sfetsos and Coonick (2000), authors proposed a
nRMSE < 2%

nRMSE 10%

MRE 8.64%

hybrid forecast model for mean global horizontal irradiance

and 13%
Forecast

(GHI) forecasting using artificial-intelligence techniques, tradi-

error

tional linear stochastic methods and adaptive neuro-fuzzy infer-

ence technique. The proposed hybrid forecast model gives higher
One week ahead
Forecast horizon

forecast accuracy than the comparative single forecast models.

4 months ahead
A review of more than one day ahead solar and PV output power forecasting techniques.

ahead forecast
120 and 160 h

Another research studies (Mellit and Kalogirou, 2008), proposed

a hybrid forecast model for GHI prediction using artificial neural
Seasonal
forecast

network and Markov transition matrices method. In Chaabene

and Ben Ammar (2008) develop a neuro fuzzy estimator based
medium term dynamic forecast model for ambient temperature
industry applications
IEEE transactions on

and irradiance with meteorological parameters. In addition,

Journal/conference

stochastic models and Kalman filtering based 5 min ahead short

IEEE conference

term was employed for meteorological parameters.

Solar Energy

In another research study investigate the performance of differ-

ent forecast models such as unobserved components models,
regressions in lags, ARIMA, neural networks and hybrid models
(Reikard, 2009; Photovoltaics, 2012; Baharudin et al., 2014). The
PV data set
Country of

finding of this study highlights that, hybrid prediction model out-

France

performs the comparative forecast models in some of the case

China

China

studies. In addition, hybrid model provides better forecast than

the single forecast in different case studies. In Martín et al.
2012
2010

2010
Year

(2010), authors design a forecast model using hybrid model ARMA

and TDNN technique for hourly solar radiation forecast.
In Ji and Chee (2011), authors designed a forecast model for
Huang et al. (2010)
Paoli et al. (2010)

hourly solar radiation series prediction model. The proposed was

Shi et al. (2012)

developed in two phases. In first phase, non-stationary trend lying

in the solar radiation series was removed using preprocessing tech-
nique. In second phase, ARMA based forecast model was used to
Table 7

Ref.

predict stationary residual series with a time delayed neural net-

work. The proposed hybrid model gives higher forecast accuracy
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 141

than the comparative forecast model. In Voyant et al. (2011),
hybrid forecast model was proposed by using optimized MLP net-
work architecture. The exogenous and meteorological variable are
applied as model input. Hybrid forecast models were also utilized
for electrical load forecasting in order to enhance the prediction
performance. In Raza and Khosravi (2015) and Raza and
Baharudin (2012) provide the detailed analysis of hybrid models
for electrical load forecast. These hybrids forecast models have a
potential to apply on PV output forecasting. There are several
hybrid techniques reported for load forecasting as given below.
models tries to forecast PV output power accurately. Due to bad
performance single model in hybrid architecture may leads may
to higher forecast error. Therefore, there is a need to design model,
in which each predictor doesn’t affect the performance of each
other. It is reported that, the multi predictor based forecast frame-
work organized in ensemble network and combined the output of
each predictor in intelligent way can enhance the overall forecast
output (Li et al., 2011). In conclusion, there is potential to apply
the ensemble based forecast framework to accurately predict to
PV output power.

 ANN with genetic Algorithms

5. Discussion
 ANN with wavelet and time series
 ANN with fuzzy and genetic algorithm
A major challenge for higher penetration (>20%) of solar energy
 ANN with Gradient Based Learning Techniques
in the grid’s ability to manage with the intrinsic variability of solar
 ANN with expert system and regression technique
renewable source. Therefore, accurate PV output power forecast
 ANN with support vector machine and artificial immune system
will assist design efficient control to deal with variability. To accu-
rately forecast the PV output power, availability of sufficient his-
Some hybrid models are also applied to solar output load fore-
torical training data and meteorological variables are very
cast in order to improve the accuracy of the model over the spec-
important. Several models were developed, which use the histori-
trum of forecast horizon. In Hernández et al. (2012), authors
cal PV output data to train the model for accurate prediction i.e.
designed a hybrid model which is based on weather classification
neural network and fuzzy logic. However, the performance of these
method and support vector machine. Different days are classified
forecast models is affected due to high PV output power ramp rate.
into clear sky, cloudy day, foggy day, and rainy day. Therefore, sup-
This due to uncertain meteorological condition, Sharpe changes in
port vector machine based forecast model was designed to predict
solar irradiances and cloud cover. In literature, research studies
the 24 h ahead load forecast. In Yona et al. (2013), authors purpose
highlight that cloud cover affect the PV output power and this
a 24 h ahead PV output power forecasting model using fuzzy the-
makes forecasting task more challenging. Several research studies
ory and neural networks (NN). Therefore, NN based forecast model
classified days into different categories to mitigate the impact of
is trained using power output data of fuzzy system and meteoro-
cloud cover on PV output power forecast. In Yang et al. (2014),
logical variables. In Yang et al. (2014) authors designed a hybrid
author design a methodology by classifying the days using self-
model using fuzzy system, self-organizing map (SOM), Support
organizing map NNs. After that, Radial Basis Function NN (RBFNN)
vector machine (SVM) and learning vector quantization (LVQ) to
is used to predict the 24 ahead PV output power. In Chen et al.
forecast the PV output power. Therefore, self-organizing map
(2011), days are divided into four classes named as cloudy, clear-
(SOM) and learning vector quantization (LVQ) used for classifica-
sky, foggy and rainy. Separate forecast model based on support
tion of PV output data. Support vector regression (SVM) used to
vector machine is used to predict the PV output power during each
train the model and fuzzy inference system is used to select the
class of days. In another research study, a hybrid technique was
better trained forecast model for higher accuracy. Therefore, there
proposed with combination of NN and fuzzy logic. At first, fuzzy
is need to design hybrid models using superior attributes of two or
model was applied to estimate hourly insolation using clouds,
more model will provide opportunity to enhance the forecast accu-
humidity and temperature. Then recurrent NN applied to forecast
racy over the spectrum of forecast horizon for different geological
the hourly PV output power. In literature, serval techniques were
PV sites.
designed to forecast PV output power during the cloudy days. As
In literature, several techniques have been applied for wind
mention earlier, some of research designed sub models or multi
power forecast, load demand and price forecast in power and
model based approaches to forecast the cloudy days. However, it
energy systems. There is potential to apply these techniques for
is observed that, the forecast error relatively higher than for cloudy
PV output power forecast to increase accuracy over the spectrum
days than the sunny days. This indicates the inability of prediction
of horizon. However, the meteorological factors such as humidity,
models not to fully capture PV output power pattern. For example,
wind speed, air temperature, cloud cover, global solar irradiance,
if training data of neural network based forecast model doesn’t
direct normal irradiance (DNI), and diffuse horizontal irradiance
contain sufficient data samples of cloudy day then, it leads to
(DHI) at solar panels add more uncertainty in PV output power.
higher prediction error. In addition, persistence model will also
In addition, physical characteristics of solar plant, solar technology
higher error if historical pattern doesn’t contain similar PV output
and other exogenous also affect the output power. Therefore, fore-
power due to high ramp rate of solar irradiation and cloud cover.
cast performance of prediction models applied on above mention
Some research studies also design the experimental photovoltaic
application may produce lower forecast results as compared other
solar radiation monitoring system, which could helpful for accu-
application. It is difficult to declare that, a single class of prediction
rate PV output power forecast.
model will suitable for PV output forecast problem. In reference
Yang et al. (2014) days are classified in groups due to variable out-
put power named as sunny and cloudy day, sunny day, cloudy day, 6. Forecast model performance evaluations matrix
cloudy and sunny day, and rainy day, cloudy and rainy day.
Authors designed six sub models with the combination of self- Generally, the steady power output is generated by the power
organizing map (SOM), learning vector quantization (LVQ) and generation sources in a stable power grid condition. However, with
support vector regression (SVR). In Haque et al. (2013) forecasted the variation of power demand it is also affect the power output. It
days are divided into three groups based on solar irradiation leads to unbalance in demand and supply (Marquez and Coimbra,
named as sunny day (SD), cloudy day (CD) and rainy day (RD). 2013; Energy, 2010). On the other side, the large variation in PV
There is possibility to design a multiple sub models to forecast output is observed as several factors are affecting on the output
the PV output power with higher accuracy. In previously reported such as solar irradiance, temperature, wind speed and humidity.
research, hybrid model based on the combination of two or more A research study in Hoff et al. (2013) suggests that, accurate PV
142 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144

qffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
PN
output forecast for different forecast horizon is required for higher 2
t¼1 ðZ t  Z t Þ
1
N
penetration of solar plants, which is able facilitate grid, ISOs and to RMSE=Capacity ¼ ð23Þ
achieve high grid stability. C
As discussed earlier, output of PV unit is largely dependent on
 rffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
the solar irradiance. In addition, a variation in solar irradiance 1 1 XN 2
can be observed as it is fundamentally dependent several factors RMSE=Capacity ¼ pffiffiffiffi ðZ t  Z t Þ ð24Þ
C N N t¼1
such as time of the day and year, climatic conditions, geographic
location and elevation techniques. In order to measure the quality
of forecasted data, correlation coefficient is measured which mea-
sure the error variance to the variance of modeled data as given in 7. Conclusions and future work
Eq. (15).
  In this paper global solar PV status and potential has been ana-
varðZ  1Þ
R2 ¼ 1  ð15Þ lyzed to meet the current global energy requirements. In the last
varðZÞ decade, large pentation of PV was observed due to tremendous
Different parameters are used to analyze and compare the fore- potential of solar energy in the different regions of the world in
cast model accuracy. Some of these parameters are discussed in terms of rooftop PV, large, medium and small scale solar plants.
this study. However, solar PV energy is can create different issues for modern
The absolute of value of the error is called Mean Absolute Error power systems directly or indirectly due to uncertain and intermit-
(MAE) which be measured by using given in Eq. (16). tent nature. Therefore, it is utmost important to accurately forecast
the PV output power.
1X N
This study provides systematic and comprehensive literature of
MAE ¼ jZ t  Zj ð16Þ
N t¼1 different solar forecasting technique. In addition, the factors affect-
ing on solar output were identified, which could be applied as fore-
where Z t is forecasted and Z is actual PV output power. A similar cast model inputs for higher accuracy. Literature indicates that, a
notation is used later equations for forecasted and actual value. certain level of forecast accuracy can be achieved by applying dif-
The Mean Absolute Percentage Error (MAPE) can be calculated by ferent stand alone and hybrid models for PV output forecast appli-
using this formula in Eq. (17). cation. It is identified that, solar irradiance, temperature, wind
N speed and direction, humidity cloud cover and aerosol index are
100% X
Z t  Z
MAPE ¼ ð17Þ major parameters to change of PV output power. It is also con-
N t¼1 Z
cluded that, solar irradiance is highly correlated with PV output
The Average spread and average bias of error can be measured power and follows the similar pattern. Therefore, the forecast accu-
by using Root mean square error (RMSE) and Mean Bias Error for- racy of prediction models can be enhanced by optimizing and bet-
mula as given in Eqs. (18) and (19) respectively. ter selection of these correlated variables.
rffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi Several attempts have been made to precisely forecast the out-
1 XN put power using different techniques in past few years. Among
RMSE ¼ ðZ t  Z t Þ2 ð18Þ
N t¼1 these techniques, regressive methods take the advantage of corre-
lated nature of meteorological variables, which are used prediction
1X N model as inputs. It is concluded that, endogenous stochastic meth-
MBE ¼ ðZ t  Z t Þ ð19Þ ods such as AR, MA, ARMA and/or ARIMA can be used where less
N t¼1
number of meteorological parameters are available as model input.
Correction coefficient can be calculated according to Eq. (20). In addition, different classification and clustering methods can be
applied for improved training the forecasting model to enhance
Cov ðx; yÞ
qx;y ¼ ð20Þ the forecast model performance. Intelligent Leaning techniques
rðxÞrðyÞ such as artificial neural network (ANN) and fuzzy logic can applied
where Cov is covariance and r indicates the standard deviation. in dynamic environment to forecast the PV output, if adequate his-
Statistical distributions observation ability of a model is known as torical patterns are available to train the network. ANN based
Kolmogorov Smirnov Integral (KSI) (Hoyer-Klick et al., 2009; model offer improved nonlinear approximation performance and
Espinar et al., 2009). KSI can calculated as given in Eq. (21). better capability to handle the uncertainty using better training
Z data and algorithm. In order to achieve the higher prediction accu-
Ymax
racy of PV output power forecast model, it is required to removed
KSI ¼ Dn dy ð21Þ
Ymin sharp changes and fluctuations in data of meteorological variables
and historical PV output power. The forecast accuracy of prediction
The cumulative distribution function difference can be repre-
models can be enhanced by pre-processing and post processing of
sented by Dn. In addition, Trapezoidal integration can used for dis-
historical and forecasted PV output power. There is also a need to
crete value of Dn. Frequency distribution reproduction can be
investigate the performance of forecast models during different
provided by using KSI (Hoff et al., 2013; Hansen, 1995). In Perez
days such as clear day, cloudy day and rainy day for further appli-
et al. (2011), also utilized KSI method to analyze the performance.
cation use. It is concluded that, the forecast performance of
A research study (Hoff et al., 2013) reports that, better relative dis-
stochastic models also affected due to individual poor perfor-
persion error can be measured by using normalized Mean Absolute
mance, model learning capability for certain PV system data, nat-
Error by using Eq. (22).
ure of meteorological events and their ramp rates. Therefore,
PN
t¼1 jZ t  Zt j
1 there is a need to design multi predictor based forecast model to
MAE=Avg ¼ N 1
PN ð22Þ mitigate the above mentions factors up to certain level. Therefore,
N t¼1 Z t
it is recommended to explore more on ensemble forecast models
This above mentioned research study also suggests that the nor- with various combination of predictors to achieve the higher pre-
malization of forecast RMSE over the maximum nominal irradiance diction accuracy. In future, accurate PV output forecast has a
cane calculated as provided in Eqs. (23) and (24). potential to utilized for different power system applications such
 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144 143

smart grid, efficient energy management system, PV integrated Hamilton, J.D., 1994. Time Series Analysis. Princeton University Press Princeton.
Hansen, B.E., 1995. Time series analysis James D. Hamilton Princeton University
smart buildings and eclectic vehicle charging, etc.
Press, 1994. Economet. Theory 11, 625–630.
Haque, A.U., Nehrir, M.H., Mandal, P., 2013. Solar PV power generation forecast
References using a hybrid intelligent approach. In: 2013 IEEE Power and Energy Society
General Meeting (PES). IEEE, pp. 1–5.
Hecht-Nielsen, R., 1987. Counterpropagation networks. Appl. Opt. 26, 4979–4984.
Ahmad, I., Abdullah, A.B., Alghamdi, AS., 2009. Application of artificial neural
Helman, U., Loutan, C., Rosenblum, G., Rothleder, M., Xie, J., Zhou, H., 2010.
network in detection of probing attacks. IEEE Symposium on Industrial
Integration of Renewable Resources: Operational Requirements and Generation
Electronics & Applications, ISIEA. IEEE, pp. 557–562.
Fleet Capability at 20% rps. California Independent System Operator.
Alfares, H.K., Nazeeruddin, M., 2002. Electric load forecasting: literature survey and
Hernández, L., Baladrón, C., Aguiar, J.M., Calavia, L., Carro, B., Sánchez-Esguevillas, A.,
classification of methods. Int. J. Syst. Sci. 33, 23–34.
Cook, D.J., Chinarro, D., Gómez, J., 2012. A study of the relationship between
Almeida, M.P., Perpiñán, O., Narvarte, L., 2015. PV power forecast using a
weather variables and electric power demand inside a smart grid/smart world
nonparametric PV model. Sol. Energy 115, 354–368.
framework. Sensors 12, 11571–11591.
Almonacid, F., Rus, C., Hontoria, L., Muñoz, F.J., 2010. Characterisation of PV CIS
Hertz, J., Krogh, A., Palmer, R.G., 1991. Introduction to the Theory of Neural
module by artificial neural networks. A comparative study with other methods.
Computation. Basic Books.
Renew. Energy 35, 973–980.
Ho, K.-L., Hsu, Y.-Y., Yang, C.-C., 1992. Short term load forecasting using a multilayer
Amral, N., Ozveren, C.S., King, D., 2007. Short term load forecasting using multiple
neural network with an adaptive learning algorithm. IEEE Trans. Power Syst. 7,
linear regression. In: 42nd International Universities Power Engineering
141–149.
Conference, UPEC, 4–6 Sept. 2007, pp. 1192–1198.
Hoff, T.E., Perez, R., Kleissl, J., Renne, D., Stein, J., 2013. Reporting of irradiance
Bacher, P., Madsen, H., Nielsen, H.A., 2009. Online short-term solar power
modeling relative prediction errors. Prog. Photovoltaics Res. Appl. 21, 1514–
forecasting. Sol. Energy 83, 1772–1783.
1519.
Baharudin, Z., Nallagownden, P., Raza, MQ., 2014. A hybrid neuro-genetic approach
Hopfield, J.J., 1982. Neural networks and physical systems with emergent collective
for STLF: a comparative analysis of model parameter variations. In: Power
computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558.
Engineering and Optimization Conference (PEOCO), 2014 IEEE 8th
Hoyer-Klick, C., Beyer, H.-G., Dumortier, D., Schroedter-Homscheidt, M., Wald, L.,
International. IEEE, pp. 526–531.
Martinoli, M., Schilings, C., Gschwind, B., Ménard, L., Gaboardi, E., 2009.
Baig, A., Akhter, P., Mufti, A., 1991. A novel approach to estimate the clear day global
MESoR-.anagement and exploitation of solar resource knowledge. In: Solar
radiation. Renew. Energy 1, 119–123.
Paces.
Boland, J., 1995. Time-series analysis of climatic variables. Sol. Energy 55, 377–388.
Huang, J., Korolkiewicz, M., Agrawal, M., Boland, J., 2013. Forecasting solar radiation
Boland, J., 2008. Time series modelling of solar radiation. In: Badescu, V. (Ed.),
on an hourly time scale using a Coupled AutoRegressive and Dynamical System
Modeling Solar Radiation at the Earth’s Surface. Springer, Berlin, Heidelberg.
(CARDS) model. Sol. Energy 87, 136–149.
Box, G.E., Jenkins, G.M., Reinsel, G.C., 2011. Time Series Analysis: Forecasting and
Huang, Y., Lu, J., Liu, C., Xu, X., Wang, W., Zhou, X., 2010. Comparative study of
Control. John Wiley & Sons.
power forecasting methods for PV stations. In: 2010 International Conference
Cao, J.C., Cao, S.H., 2006. Study of forecasting solar irradiance using neural networks
on Power System Technology (POWERCON). IEEE, pp. 1–6.
with preprocessing sample data by wavelet analysis. Energy 31, 3435–3445.
(IEA), I.E.A., 2007. International Organization for Standardization (IEA–ISO).
Chaabene, M., Ben Ammar, M., 2008. Neuro-fuzzy dynamic model with Kalman
International standards to develop and promot energy efficiency and
filter to forecast irradiance and temperature for solar energy systems. Renew.
renewable energy sources. Special ISO focus—world energy congress, 5–10.
Energy 33, 1435–1443.
Jain, L.C., Martin, N., 1998. Fusion of Neural Networks, Fuzzy Systems and Genetic
Chakhchoukh, Y., Panciatici, P., Mili, L., 2011. Electric load forecasting based on
Algorithms: Industrial Applications. CRC Press.
statistical robust methods. IEEE Trans. Power Syst. 26, 982–991.
Ji, W., Chee, K.C., 2011. Prediction of hourly solar radiation using a novel hybrid
Chen, C., Duan, S., Cai, T., Liu, B., 2011. Online 24-h solar power forecasting based on
model of ARMA and TDNN. Sol. Energy 85, 808–817.
weather type classification using artificial neural network. Sol. Energy 85,
Jordan, M.I., 1997. Serial order: a parallel distributed processing approach. Adv.
2856–2870.
Psychol. 121, 471–495.
Chen, J.-F., Wang, W.-M., Huang, C.-M., 1995. Analysis of an adaptive time-series
Junior, J.G.D.S.F., Oozeki, T., Ohtake, H., Shimose, K.-I., Takashima, T., Ogimoto, K.,
autoregressive moving-average (ARMA) model for short-term load forecasting.
2014. Forecasting regional photovoltaic power generation – a comparison of
Electr. Power Syst. Res. 34, 187–196.
strategies to obtain one-day-ahead data. Energy Procedia 57, 1337–1345.
Christiaanse, W.R., 1971. Short-term load forecasting using general exponential
Kang, M.-C., Sohn, J.-M., Park, J.-Y., Lee, S.-K., Yoon, Y.-T., 2011. Development of
smoothing. IEEE Trans. Power App. Syst. PAS-90, 900–911.
algorithm for day ahead PV generation forecasting using data mining method.
Chu, Y., Urquhart, B., Gohari, S.M.I., Pedro, H.T.C., Kleissl, J., Coimbra, C.F.M., 2015.
In: 2011 IEEE 54th International Midwest Symposium on Circuits and Systems
Short-term reforecasting of power output from a 48 MWe solar PV plant. Sol.
(MWSCAS). IEEE, pp. 1–4.
Energy 112, 68–77.
Kaplanis, S.N., 2006. New methodologies to estimate the hourly global solar
Chua, L.O., Yang, L., 1988. Cellular neural networks: applications. IEEE Trans. Circ.
radiation; comparisons with existing models. Renew. Energy 31, 781–790.
Syst. 35, 1273–1290.
Kasten, F., Young, A.T., 1989. Revised optical air mass tables and approximation
Chupong, C., Plangklang, B., 2011. Forecasting power output of PV grid connected
formula. Appl. Opt. 28, 4735–4738.
system in Thailand without using solar radiation measurement. Energy Proc. 9,
Kaur, A., Pedro, H.T.C., Coimbra, C.F.M., 2013. Impact of onsite solar generation on
230–237.
system load demand forecast. Energy Convers. Manage. 75, 701–709.
Cococcioni, M., D’andrea, E., Lazzerini, B., 2011. 24-hour-ahead forecasting of energy
Kemmoku, Y., Orita, S., Nakagawa, S., Sakakibara, T., 1999. Daily insolation
production in solar PV systems. In: 2011 11th International Conference on
forecasting using a multi-stage neural network. Sol. Energy 66, 193–199.
Intelligent Systems Design and Applications (ISDA). IEEE, pp. 1276–1281.
Khotanzad, A., Enwang, Z., Elragal, H., 2002. A neuro-fuzzy approach to short-term
Council, T.E., 2010. Communication from the Commission to the European
load forecasting in a price-sensitive environment. IEEE Trans. Power Syst. 17,
Parliament. The European Economic and Social Committee and the
1273–1282.
Committee of the Regions.
Kostylev, V., Pavlovski, A., 2011. Solar power forecasting performance–towards
de Giorgi, M.G., Congedo, P.M., Malvoni, M., 2014. Photovoltaic power forecasting
industry standards. In: 1st International Workshop on the Integration of Solar
using statistical methods: impact of weather data. IET Sci. Meas. Technol. 8, 90–
Power into Power Systems Aarhus, Denmark.
97.
Lai, L.L., 1998. Intelligent System Applications in Power Engineering: Evolutionary
Denholm, P., Margolis, R.M., 2007. Evaluating the limits of solar photovoltaics (PV)
Programming and Neural Networks. John Wiley & Sons Inc.
in traditional electric power systems. Energy Policy 35, 2852–2861.
Leva, S., Dolara, A., Grimaccia, F., Mussetta, M., Ogliari, E., 2015. Analysis and
Ding, M., Wang, L., Bi, R., 2011. An ANN-based approach for forecasting the power
validation of 24 hours ahead neural network forecasting of photovoltaic output
output of photovoltaic system. Proc. Environ. Sci. 11 (Part C), 1308–1315.
power. Math. Comput. Simul., 0378-4754. http://dx.doi.org/10.1016/
Dixon, R.K., McGowan, E., Onysko, G., Scheer, R.M., 2010. US energy conservation
j.matcom.2015.05.010.
and efficiency policies: challenges and opportunities. Energy Policy 38, 6398–
Li, G., Shi, J., Zhou, J., 2011. Bayesian adaptive combination of short-term wind speed
6408.
forecasts from neural network models. Renew. Energy 36, 352–359.
Dolara, A., Leva, S., Manzolini, G., 2015. Comparison of different physical models for
Lipperheide, M., Bosch, J., Kleissl, J., 2015. Embedded nowcasting method using
PV power output prediction. Sol. Energy 119, 83–99.
cloud speed persistence for a photovoltaic power plant. Sol. Energy 112, 232–
Elman, J.L., 1990. Finding structure in time. Cogn. Sci. 14, 179–211.
238.
Energy, G., 2010. Western Wind and Solar Integration Study. Citeseer.
Liu, J., Fang, W., Zhang, X., Yang, C., 2015. An Improved photovoltaic power
Espinar, B., Ramírez, L., Drews, A., Beyer, H.G., Zarzalejo, L.F., Polo, J., Martín, L., 2009.
forecasting model with the assistance of aerosol index data. IEEE Trans. Sustain.
Analysis of different comparison parameters applied to solar radiation data
Energy 6, 434–442.
from satellite and German radiometric stations. Sol. Energy 83, 118–125.
Lonij, V.P.A., Brooks, A.E., Cronin, A.D., Leuthold, M., Koch, K., 2013. Intra-hour
Fausett, L., 2006. Fundamentals of Neural Networks: Arquitectures, Algorithms, and
forecasts of solar power production using measurements from a network of
Applications. Pearson Education India.
irradiance sensors. Sol. Energy 97, 58–66.
Gohari, M.I., Urquhart, B., Yang, H., Kurtz, B., Nguyen, D., Chow, C.W., Ghonima, M.,
Lorenz, E., Scheidsteger, T., Hurka, J., Heinemann, D., Kurz, C., 2011. Regional PV
Kleissl, J., 2014. Comparison of solar power output forecasting performance of
power prediction for improved grid integration. Prog. Photovoltaics Res. Appl.
the total sky imager and the University of California, San Diego Sky Imager.
19, 757–771.
Energy Proc, 49, 2340–2350.
Lucheroni, C., 2009. A Resonating Model for the Power Market and its Calibration.
Hahn, H., Meyer-Nieberg, S., Pickl, S., 2009. Electric load forecasting methods: tools
SSRN: <http://ssrn.com/abstract>.
for decision making. Eur. J. Oper. Res. 199, 902–907.
144 M.Q. Raza et al. / Solar Energy 136 (2016) 125–144
Madan, M., Liang, J., Noriyasu, H., 2003. Static and Dynamic Neural Networks: From
Fundamentals to Advanced Theory. John Wiley & Sons, Canada.
Malki, H.A., Karayiannis, N.B., Balasubramanian, M., 2004. Short-term electric power
load forecasting using feedforward neural networks. Expert Syst. 21, 157–167.
Mandal, P., Madhira, S.T.S., Haque, A.U., Meng, J., Pineda, R.L., 2012. Forecasting
power output of solar photovoltaic system using wavelet transform and
artificial intelligence techniques. Proc. Comput. Sci. 12, 332–337.
Marín, F.J., Sandoval, F., 1997. Short-term peak load forecasting: statistical methods
versus artificial neural networks. In: Mira, J., Moreno-Díaz, R. (Eds.), From
Neuroscience to Technology Biological and Artificial Computation. Springer,
Berlin, Heidelberg.
Marquez, R., Coimbra, C.F., 2013. Proposed metric for evaluation of solar forecasting
models. J. Sol. Energy Eng. 135, 011016.
Martín, L., Zarzalejo, L.F., Polo, J., Navarro, A., Marchante, R., Cony, M., 2010.
Prediction of global solar irradiance based on time series analysis: application
to solar thermal power plants energy production planning. Sol. Energy 84,
1772–1781.
Mathiesen, P., Kleissl, J., 2011. Evaluation of numerical weather prediction for intra-
day solar forecasting in the continental United States. Sol. Energy 85, 967–977.
McCulloch, W.S., Pitts, W., 1943. A logical calculus of the ideas immanent in nervous
activity. Bull. Math. Biophys. 5, 115–133.
Mellit, A., Kalogirou, S.A., 2008. Artificial intelligence techniques for photovoltaic
applications: a review. Prog. Energy Combust. Sci. 34, 574–632.
Mohamed, Z., Bodger, P.S., 2004. Forecasting Electricity Consumption: A
Comparison of Models for New Zealand.
Mori, H., Takahashi, M., 2012. Development of GRBFN with global structure for PV
generation output forecasting. In: 2012 IEEE Power and Energy Society General
Meeting. IEEE, pp. 1–7.
Morris, R., 1999. DO Hebb: the organization of behavior, Wiley: New York; 1949.
Brain Res. Bull. 50, 437.
Mueller, R.W., Dagestad, K.F., Ineichen, P., Schroedter-Homscheidt, M., Cros, S.,
Dumortier, D., Kuhlemann, R., Olseth, J.A., Piernavieja, G., Reise, C., Wald, L.,
Heinemann, D., 2004. Rethinking satellite-based solar irradiance modelling: the
SOLIS clear-sky module. Rem. Sens. Environ. 91, 160–174.
Nilsson, N.J., 1965. Learning Machines.
Omran, W. Performance Analysis of Grid-connected Photovoltaic System. PhD
Dissertation. PhD, University of Waterloo.
Oudjana, S., Hellal, A., Mahammed, I.H., 2013. Power forecasting of photovoltaic
generation. Int. J. Electr. Electron. Sci. Eng., 7
Paoli, C., Voyant, C., Muselli, M., Nivet, M.-L., 2010. Forecasting of preprocessed daily
solar radiation time series using neural networks. Sol. Energy 84, 2146–2160.
Patterson, D.W., 1998. Artificial Neural Networks: Theory and Applications. Prentice
Hall PTR.
Pedro, H.T.C., Coimbra, C.F.M., 2012. Assessment of forecasting techniques for solar
power production with no exogenous inputs. Sol. Energy 86, 2017–2028.
Pelland, S., Galanis, G., Kallos, G., 2013. Solar and photovoltaic forecasting through
post-processing of the global environmental multiscale numerical weather
prediction model. Prog. Photovoltaics Res. Appl. 21, 284–296.
Perez, R., Beauharnois, M., Hemker, K., Kivalov, S., Lorenz, E., Pelland, S., Schlemmer,
J., Van knowe, G., 2011. Evaluation of numerical weather prediction solar
irradiance forecasts in the US. In: ASES Annual Conference. Raleigh, NC, USA, p.
011.
Perez, R., Kivalov, S., Schlemmer, J., Hemker, K., Renné, D., Hoff, T.E., 2010. Validation
of short and medium term operational solar radiation forecasts in the US. Sol.
Energy 84, 2161–2172.
Photovoltaics, S., 2012. Renewable Energy Technologies: Cost Analysis Series.
International Renewable Energy Agency (IRENA) Working Paper.
Ramsami, P., Oree, V., 2015. A hybrid method for forecasting the energy output of
photovoltaic systems. Energy Convers. Manage. 95, 406–413.
Raza, M.Q., Baharudin, Z., 2012. A review on short term load forecasting using
hybrid neural network techniques. In: Power and Energy (PECon), 2012 IEEE
International Conference on, 2–5 Dec. 2012, pp. 846–851.
Raza, M.Q., Baharudin, Z., Badar-Ul-islam, B.-U.-I., Nallagownden, P., 2014. A
comparative analysis of neural network based short term load forecast models
for anomalous days load prediction. J. Comput. 9, 1519–1524.
Raza, M.Q., Khosravi, A., 2015. A review on artificial intelligence based load demand
forecasting techniques for smart grid and buildings. Renew. Sustain. Energy
Rev. 50, 1352–1372.
Reikard, G., 2009. Predicting solar radiation at high resolutions: a comparison of
time series forecasts. Sol. Energy 83, 342–349.
Rezk, H., Tyukhov, I., Raupov, A., 2015. Experimental implementation of
meteorological data and photovoltaic solar radiation monitoring system. Int.
Trans. Electr. Energy Syst. 25, 3573–3585.
View publication stats
Rivas, V.M., Merelo, J.J., Castillo, P.A., Arenas, M.G., Castellano, J.G., 2004. Evolving
RBF neural networks for time-series forecasting with EvRBF. Inf. Sci. 165, 207–
220.
Rodrigyuez, G.D., 2010. A utility perspective of the role of energy storage in the
smart grid. In: Power and Energy Society General Meeting, 2010 IEEE, 25–29
July 2010, pp. 1–2.
Rosenblatt, F., 1962. Principles of Neurodynamics.
Sansa, I., Missaoui, S., Boussada, Z., Bellaaj, N.M., Ahmed, E.M., Orabi, M., 2014. PV
power forecasting using different artificial neural networks strategies. In: 2014
International Conference on Green Energy. IEEE, pp. 54–59.
Sfetsos, A., Coonick, A.H., 2000. Univariate and multivariate forecasting of hourly
solar radiation with artificial intelligence techniques. Sol. Energy 68, 169–178.
Shah, B.M., Syahiman, A., Yokoyama, H., Kakimoto, N., 2015. High-precision
forecasting model of solar irradiance based on grid point value data analysis
for an efficient photovoltaic system. IEEE Trans. Sustain. Energy 6, 474–481.
Shah, R., Mithulananthan, N., Bansal, R., Ramachandaramurthy, V., 2015. A review of
key power system stability challenges for large-scale PV integration. Renew.
Sustain. Energy Rev. 41, 1423–1436.
Shekhar, S., Amin, M.B., 1992. Generalization by neural networks. IEEE Trans.
Knowl. Data Eng. 4, 177–185.
Shi, J., Lee, W.-J., Liu, Y., Yang, Y., Wang, P., 2012. Forecasting power output of
photovoltaic systems based on weather classification and support vector
machines. IEEE Trans. Ind. Appl. 48, 1064–1069.
Smith, C., Jin, Y., 2014. Evolutionary multi-objective generation of recurrent
neural network ensembles for time series prediction. Neurocomputing 143,
302–311.
Soman, S.S., Zareipour, H., Malik, O., Mandal, P., 2010. A review of wind power and
wind speed forecasting methods with different time horizons. In: North
American Power Symposium (NAPS), 2010, 26–28 Sept. 2010, pp. 1–8.
Tao, Y., Chen, Y., 2014. Distributed PV power forecasting using genetic algorithm
based neural network approach. In: 2014 International Conference on Advanced
Mechatronic Systems (ICAMechS). IEEE, pp. 557–560.
Tasre, M.B., Bedekar, P.P., Ghate, V.N., 2011. Daily peak load forecasting using ANN.
In: Nirma University International Conference on Engineering (NUiCONE). IEEE,
pp. 1–6.
Tuyishimire, B., Mccann, R., Bute, J., 2013. Evaluation of a Kalman predictor
approach in forecasting PV solar power generation. In: 2013 4th IEEE
International Symposium on Power Electronics for Distributed Generation
Systems (PEDG). IEEE, pp. 1–6.
UQ solar <http://solar-energy.uq.edu.au/> [Online]. [Accessed].
Voyant, C., Muselli, M., Paoli, C., Nivet, M.-L., 2011. Optimization of an artificial
neural network dedicated to the multivariate forecasting of daily global
radiation. Energy 36, 348–359.
Wengenmayr, R., Bührke, T., 2011. Renewable Energy: Sustainable Energy Concepts
for the Future. John Wiley & Sons.
Widrow, B., Hoff, M.E., 1960. Adaptive Switching Circuits.
Widrow, B., Winter, R., 1988. Neural nets for adaptive filtering and adaptive pattern
recognition. Computer 21, 25–39.
Williams, R.J., Zipser, D., 1989. Experimental analysis of the real-time recurrent
learning algorithm. Connect. Sci. 1, 87–111.
Yang, C., Thatte, A., Xie, L., 2015. Multitime-scale data-driven spatio-temporal
forecast of photovoltaic generation. IEEE Trans. Sustain. Energy 6, 104–112.
Yang, H.-T., Huang, C.-M., Huang, Y.-C., Pai, Y.-S., 2014. A weather-based hybrid
method for 1-day ahead hourly forecasting of PV power output. IEEE Trans.
Sustain. Energy 5, 917–926.
Yona, A., Senjyu, T., Funabashi, T., Chul-Hwan, K., 2013. Determination method of
insolation prediction with fuzzy and applying neural network for long-term
ahead PV power output correction. IEEE Trans. Sustain. Energy 4, 527–533.
Zagouras, A., Pedro, H.T.C., Coimbra, C.F.M., 2015. On the role of lagged exogenous
variables and spatio–temporal correlations in improving the accuracy of solar
forecasting methods. Renew. Energy 78, 203–218.
Zervos, A., 2015. Renewables 2015 Global Status Report. REN 21.
Zervos, A., Lins, C., Muth, J., 2010. RE-thinking 2050: a 100% Renewable Energy
Vision for the European Union, EREC.
Zhang, H.L., Baeyens, J., Degrève, J., Cacères, G., 2013. Concentrated solar power
plants: review and design methodology. Renew. Sustain. Energy Rev. 22, 466–
481.
Zhang, J.-R., Zhang, J., Lok, T.-M., Lyu, M.R., 2007. A hybrid particle swarm
optimization-back-propagation algorithm for feedforward neural network
training. Appl. Math. Comput. 185, 1026–1037.
Zhang, J., Florita, A., Hodge, B.-M., Lu, S., Hamann, H.F., Banunarayanan, V.,
Brockway, A.M., 2015. A suite of metrics for assessing the performance of
solar power forecasting. Sol. Energy 111, 157–175.