Forecasting and Scheduling

RENEWABLES

14/02/2024 1
14/02/2024 2
14/02/2024 3
14/02/2024 4
14/02/2024 5
14/02/2024 6
14/02/2024 7
 FROM CLIP BOARD

14/02/2024 8
14/02/2024 9
14/02/2024 10
14/02/2024 11
14/02/2024 12
14/02/2024 13
14/02/2024 14
14/02/2024 15
14/02/2024 16
14/02/2024 17
 SDF: Similar Day Forecasting
• 7 days a week X 12 months a year + 12
holidays
= 96 days hourly demand profile
• The weather parameters are:
– Temperature
– Pressure
– Humidity
– Rainfall
– Wind speed

POWERGRID, ERLDC 18
 SDF: Similar Day Forecasting
• Weather data can be calculated by the following
formula
H (T) = H(X) + [H(Y) – H(X)] X (T-X)
Where, Y-X
H – Value of weather parameters at specified hour
X – Pre defined hour
Y – Next pre defined hour
T – Hour between the range x & y for which the calculation is
performed.

POWERGRID, ERLDC 19
Forecasting, Scheduling of Solar / Wind (6.5 (23))
• Wind and Solar generators shall mandatorily provide to the concerned
RLDC, in a format as prescribed by RLDC, the technical specifications at
the beginning and whenever there is any change.
• Forecasting shall be done by wind and solar generators which are regional
entities as well as the concerned RLDC.
• Wind and solar energy generation forecast with an interval of 15 minutes for
the next 24 hours for the aggregate generation capacity of 50 MW and above

20
RE forecasting & Scheduling
Scheduling & Settlement of Solar / Wind (6.5 (23))
• The schedule by wind and solar generators may be revised by giving advance notice
to the concerned RLDC , Such revisions shall be effective from 4th time block.
• One revision for each time slot of one and half hours starting from 00:00 hours (Max
16 revisions per day)
• The schedule of solar generators which are regional entities shall be given by the
generator based on availability of the generator, weather forecasting, solar
insolation/irradiance, season and normal solar generation curve .
• The charges payable for deviation from schedule by the wind and solar generators,
shall be delinked from frequency and shall be accounted for and settled in
accordance with the provisions of the Central Electricity Regulatory Commission
(Deviation Settlement Mechanism and related matters) Regulations, 2014 as
amended from time to time
21
Physical Regulation for excess deviation
 Methods of Load Forecasting
Short Term Load Forecasting

Methods of Short Term Load forecasting

Similar-day approach

Regression methods

Time series

Neural networks

Expert systems

Fuzzy logic.
 Methods of Load Forecasting
Short Term Load Forecasting
Similar-day approach

This approach is based on searching historical data for days within

one, two, or three years with similar characteristics
to the forecast day.
Similar characteristics include weather, day of the week, and the
date. The load of a similar day is considered as a forecast.
Instead of a single similar day load, the forecast can be a linear
combination or regression procedure that can include several
similar days.
The trend coefficients can be used for similar days in the previous
years.
 Methods of Load Forecasting
Short Term Load Forecasting

Regression methods
used to model the relationship of load consumption and other
factors such as weather, day type, and customer class.
several regression models for the next day peak forecasting. Their
models incorporate deterministic influences such as holidays,
stochastic influences such as average loads, and exogenous
influences such as weather.
 Methods of Load Forecasting
Short Term Load Forecasting
Time series

Time series methods are based on the assumption that

the data have an internal structure, such as autocorrelation, trend,
or seasonal variation. Time series forecasting methods detect and
explore such a structure. Time series have been used for decades in
such fields as economics, digital signal processing, as well as
electric load forecasting.
 Methods of Load Forecasting
Short Term Load Forecasting
Time series
ARMA (autoregressive moving average),
ARIMA (autoregressive integrated moving average),
ARMAX (autoregressive moving average with exogenous variables),
ARIMAX (autoregressive integrated moving average with exogenous
variables) are the most often used classical time series methods.
ARMA models are usually used for stationary processes while ARIMA is an
extension of ARMA to nonstationary
processes.
ARMA and ARIMA use the time and load as the only input parameters.
Since load generally depends on the weather and time of the day,
ARIMAX is the most natural tool for load forecasting among the
classical time series models.
 Methods of Load Forecasting
Short Term Load Forecasting

Neural networks

The use of artificial neural networks (ANN) has been a widely

studied electric load forecasting technique since
1990.
Neural networks are essentially non-linear circuits that
have the demonstrated capability to do non-linear curve fitting.
The outputs of an artificial neural network are some linear or
nonlinear mathematical function of its inputs. The inputs may be
the outputs of other network elements as well as actual network
inputs.
In practice network elements are arranged in a relatively small
number of connected layers of elements between network inputs
and outputs. Feedback paths are sometimes used.
 Methods of Load Forecasting
Short Term Load Forecasting

Neural networks

In applying a neural network to electric load forecasting, one must

select one of a number of architectures (e.g. Hopfield, back
propagation, Boltzmann machine), the number and connectivity of
layers and elements, use of bi-directional or uni-directional links,
and the number format (e.g. binary or continuous) to be used by
inputs and outputs,and internally.

The most popular artificial neural network architecture for electric

load forecasting is back propagation.
Back propagation neural networks use continuously valued
functions and supervised learning.
 Methods of Load Forecasting
Short Term Load Forecasting

Expert systems

Rule based forecasting makes use of rules, which are

often heuristic in nature, to do accurate forecasting.

Expert systems incorporates rules and procedures used by human

experts in the field of interest into software that is then able to
automatically make forecasts without human assistance.

This rule base is complemented by a parameter database that

varies from site to site.
 Methods of Load Forecasting
Short Term Load Forecasting
Fuzzy logic

Fuzzy logic is a generalization of the usual Boolean logic

used for digital circuit design. An input under Boolean logic takes on a truth value
of “0” or “1”.
Under fuzzy logic an input has associated with it a certain qualitative ranges.

For instance a transformer load may be “low”, “medium” and “high”.

Fuzzy logic allows one to (logically) deduce outputs from fuzzy inputs. In this
sense fuzzy logic is one of a number of techniques for mapping inputs to outputs
(i.e. curve fitting).

Among the advantages of fuzzy logic are the absence of a need for a mathematical
model mapping inputs to outputs and the absence of a need for precise (or even
noise free) inputs.
 Methods of Load Forecasting

The development and improvements of appropriate mathematical

tools will lead to the development of more
accurate load forecasting techniques. The accuracy of load
forecasting depends not only on the load forecasting techniques,
but also on the accuracy of forecasted weather scenarios.
14/02/2024 32
14/02/2024 33
 Auto Regressive (AR)

In the AR process, the current value of the time series

y(t) is expressed linearly in terms of its previous
values y(t-1), y(t-2)…..) and a random noise a(t).

The order of this process depends on the oldest

previous value at which y(t) is regressed on.

14/02/2024 34
 Multiple Linear Regression (MLR)

The load is found in terms of explanatory variables

such as weather and non-weather variables which
influence the electrical load. The load model using
this method is expressed in the form as.
y(t) = ao + a1X1(t) + …….+anXn(t) +a(t)
y(t) = electrical load
X1(t) + …….Xn(t) = explanatory variables correlated
with y(t)
a(t) = a random variable with zero mean and
constant variance ao, a1…….an = regression
coefficients
14/02/2024 35
14/02/2024 36
14/02/2024 37
14/02/2024 38
14/02/2024 39
14/02/2024 40
14/02/2024 41
14/02/2024 42
14/02/2024 43
14/02/2024 44
14/02/2024 45
14/02/2024 46
14/02/2024 47
14/02/2024 48
14/02/2024 49
14/02/2024 50
14/02/2024 51
14/02/2024 52
14/02/2024 53
14/02/2024 54
14/02/2024 55
14/02/2024 56
14/02/2024 57
14/02/2024 58
14/02/2024 59
14/02/2024 60
14/02/2024 61
14/02/2024 62
14/02/2024 63
14/02/2024 64
14/02/2024 65
14/02/2024 66
14/02/2024 67
14/02/2024 68
14/02/2024 69
14/02/2024 70
14/02/2024 71
14/02/2024 72
14/02/2024 73
14/02/2024 74
14/02/2024 75
14/02/2024 76
14/02/2024 77
14/02/2024 78
14/02/2024 79
14/02/2024 80
14/02/2024 81
THANK YOU

82