POWer SyStemS:/ans f/erst., VOl. 27, model:/ fker SouIeS, VO1 262, PP. 5061, [43] K.

5061, [43] K. Ngamsal and A Arpornwichanop, Anal-

no. 1, PP. 323-334, Feb. 2012.
[131 C. M. Johnstone, D. Pratt, J. A. Clarke, and A.
D. Grant`A techno-eCOnOmic analysis of tidal
enelgy teChnoIogy:Rene! Enegy, VOl. 49, PP.
101-106, Jan. 2013
[14 E. J. Coster, J M. A. Myrzik, B. Krulmer, and
W. L. Klingtegration lSSueS Of distrlbuted
generation in distribution grids:Proc /E,
VOl. 99, nO. l, PP. 28-39, Jan. 2011
[15] J. M. Carrasco, L. C. Franquelo, J. T. Blalasle-
Wicz, E. Galvan, R. C. PortiIIo GulSado, M A
Martfn Prats, J. I. Le6n, and N Moreno-lfonso,
Power-electronic systems for the grid lntegra-
tlOn Of renewable energy sourcesA survey:
os hd Elec, VO1 53, nO. 4, pp.
1002-1016, Aug 2006.
[16] J. Kondoh, I. Ishll, H. Yamaguchl, Murata,
K Otani, K. Sakuta, N. HiguchS. Seklne,
and M Kamimoto, ``Electrical eIlergy StOrage
SyStemS for energy networks:ergy Conu
Mcmog, VO1 41, nO n. 17, PP 1863-1874, Nov.
2000
[17] B. P. Roberts and C. Sandberg, `The role of en-
ergy storage in development of smart grids:
Proc RE, VOl. 99, nO. 6, PP 1139-1144, June
2011.
[18] T Hemessy, Overcoming tansmission con-
Straints: energy StOrage and Wyoming wlnd
POWer. DOE energy storage systems research
PrOgram annual peer review:Washington,
D.C., Nov 2006
[19] J P. Barton and D. G Infield, Energystorage
and ltS uSe Wlth intermittent renewable ener-
gy:ins EneI 00ers., VO=9, nO. 2,
PP 44l-448, June 2004
[20 R. Poudlneh and T. Jamasb, DIStrlbuted gen-
eration, StOrage, demand response and energy
Sept. 2014. ysIS and measurement of the electrolyte
imbalance in a vanadlum redox flow battery,
29 A. Parasuraman,T M. Lim, C Menictas,andM
J of Po(Oer 50eS, VOl. 282, Pp. 534-543,
Sky=as-Kazacos, Review of materlaesearch
and development for vanadium redox flow bat-
May 2015.
tery applications:E/ectrochim Acto, VOl. 101, [44] V. Yu, A. Headley, and D. ChenA constrained
PP. 27-40, July 2013. extended Kalman fllter for state-Of-Charge estl-
mation of a vanadium redox flow battery wlth
30] S. Won, K. Oh, and H. Ju, NumerlCal analysis
CrOSSOVer effects:ASMJ DVI fys, Meos,
Of vanadlum CrOSSOVer effects ln all-Vanadium
CbroI, VOL 136, nO. 4
redox flow batterleS:E/ectOChIm Acta, VOl.
177, PP. 310-320, Sept. 2015. 45] P Gao, C Zhang, and G. Wen, Equivalent
Circuit model analysis on electrochemical
[31] X. G. Yang, O. Ye, P. Cheng, and T. S Zhao, Ef-
impedance spectroscopy of lithium metal ba
fects of the electrlC fleld on ion crossover in
terleS:J Pot)er Sources, VOl. 294, PP. 67-74,
Vanadium redox =ow batterleS:App/ey,
Oct 2015.
VOl 145, PP 306-319, May2015
[46 C de Beer, P. S Barendse, and P. Pillay`Fuel
[32] K. Ngamsai and A. Arpomwichanop`AnalysIS
Cell condltion monitoring using optlmlZed
and measurement of the electrolyte imbalance
broadband lmPedance spectroscopy:
in a vanadlum redox flow battery:/ Po(t,er
7TnS hod EIec[ron, VO1 62, nO 8, PP. 5306-
SotJrCeS, VO1 282, PP. 534-543, May 2015
5316, ug. 2015.
33 S K6nig, M R. Suriyah, and T. Lelbfrled,
Model based examlnat10n On influence of [47 Project HELTH-CODE. Real operation pem
fuel ce11s HEALTH-State mOnitoring and dlag-
StaCk series connection and pipe diameters
nosis based on dc-dc Converter embedded
On efficlenCy Of vanadlum redox flow batter-
EIS. H2020-JTI-FCH-2014-1. [Online Avallable:
1eS under conslderation of shunt currents,i
http:www.pemfc.health-COde eu
J Po(t,er Sources, VOl. 28l, PP 272-284, May
2015 [48] S Kouro, J. L Leon, D. Vlnnikov, and L. G.
Franquelo, 2Grid-COnneCted photovoltaic
[34] S. Kim, E. Thomsen, G. Xia, Z. Nle, J. Bao, K. SyStemS: An overvleW Of recent research and
Recknagle, W Wang, V Viswanathan, O. Luo,
emerglng PV converter technoIogy:/E hod
X Wei, A. Crawford, G Coffey, G. Maupin, and
Elec[ron Wog, VOl. 9, nO. l, PP. 4761, March
V Sprenkle, 1 kW/1 kWh advanced vanadium
2015.
redox flow battery utlllZlng mixed acld Electro-
1ytes,J Po(ter SoeS, VOl. 237, PP. 300-309, [49] B Zhao, O Song, W. Liu, and Y. Sun, Over-
Sept 2013. VleW Of dual-aCtlVe-bridge isolated bldirec-
tlOnal dc-dc converter for high-frequency-
135] D.S.Aaron,Q. Liu,Z.ng,G.M Grim,.B llnk power-COnVerSion system:/EEE 7)OrlS
Papandrew, A. Turhan, T. A. Zawodzinski, and
Po[erEIec[ron , VOl. 29, nO. 8, PP 409l-4106,
M M Mench, Dramatic perfomance gains in
Aug. 2014.
Vanadium redox flow batteries through mod
fled cell architecture:/)eSotJrCeS, VOl. 206, [50] F Krismer and J W KolarEfficiency-OPt

efficiency as alternatlVeS tO grld capaclty en-
hancement,eIgyPo/icy, VO1 67, PP 222231,
Apr. 2014.
21] S Sundararagavan and E. Baker, Evaluating
energy storage technoIogies for wind power
integration:SoIergy, VOl 86, PP 2707-2717,
Sept. 2012
22] A. Zahedl, MaxlmlZlng SOlar PV energy pen-
etration using energy storage technoIogy:Re-
neSus!eReVO=5, pp. 866-870, Jan
2011
[23] C. Pieper and H Rubel, Revisiting energystor-
age There is a business case:i Boston Consul
ing Group Report, Feb. 201l.
[24] W F PICkard, A Q Shen, and N. J. Hanslng,
Parklng the power: Strategies and physical
limitations for bulk energy storage in supply-
demand matchlngOn agrld whose mPut POWer
lS PrOVided by intermittent sources,Rene(
5us[. EneJg Reu. vol. 13, PP. 1934-1945, Oct
2009.
[25] B. Dunn, H Kamath and J TarasconElectr
Cal energy storage for the grld a battery of
Choices,SclenCe, VOl. 334, nO. 6058, PP. 928-
935, Nov. 2011.
[26] G L. Soloveichik, FIow batteries: Current sta-
tus and trends:Chem Reu , VO=15, nO. 20, PI).
11,533-11,558, Sept 2015.
[27] K. Knehr and E. KumburOpen circuit voltage
Ofvanadium redox flow batterleS DISCrePanCy
between models and experiments:Electro-
Chem Commun, VO1 13, nO. 4, PP342-345,
Apr 2011.
[28] B. Xiong, J. Zhao, Z. Wel, and M. Sky11as-Kaza-
COS, Extended Kalman filter method for state
Of charge estlmation of vanadlum redox flow
battery uslng thermal-dependent electrical
pp 450-453, May2012
[36] D MaggioIo,F Picano, A. MarlOn, and M. Guar-
neri, AppllCatlOn O=he Lattice-Boltzmam
method for modeling alvanadium redox flow
batteries,n POC /V ht Coni PartICIe-Bosed
Methods-ndameoIs md AppIICO/10nS-
Par[!C/e 20I5, Sept 28-30, 2015, PP. 579-589.
i37 P AIotto, M Guamierl, F. Moro, and A. Stella,
Multphysic 3D dynamic modelling of poly-
mer membranes with a proper generalized
decompositlOn mOdel reduction approach
Electrochlm Ac/0, VO1 57, nO l, PP. 250-256,
Dec. 2011.
[38] Q.Xu and T. S. Zhao, Fundamental models for
flow batteries,POgr Ene)gy Combus/ Sc
VOl 49, PP. 40-58, Aug 2015
[39 Q. Zheng, X. Ll, Y. Cheng, G. Ning, F Xlng, and
F Zhang, `Development and perspective in va-
nadium flow battery modeling,App/ Ene}gy,
VO=32, PP. 254-266, Nov. 2014.
[40] X Qiu, T. A. Nguyen, J. D Guggenberger, M.
L. Crow, and A. C. Elmore, A field validated
model of a vanadium redox llow battery for
microgrids:7Jans. Smar( GrId, VOl. 5, nO.
4, pp 1592-160l,July2014.
[41 B. Xiong, J. Zhao, Z. Wel, and M. Sky=as-Kaza-
COS, Extended Kalman fllter method for state
Of charge estlmat10n Of vanadlum redox flow
battery using thermal-dependent electricaI
model,/ PoOer SouCeS, VOl. 262, PP. 50-61,
Sept. 2014
[42 M. J. WatSmith, P. Ridley, R. G. A. Wills, A. .
Shah, and F. C. Walsh`The lmPOrtanCe Of key
OPeratlOnal variables and electrolyte monltOr-
ing to the performance of an all vanadium re-
dox flow batlery,i / !em 7chnoI BIOteChnoI,
VOL88,nO l,pp 126-138,Jan.2013
mlZed hlgh-Current dual active brldge con-
Verter for automotive applications,EE
7Jons hd ETec/ron, VO1 59, nO. 7, PP. 2745-
2760, July 2012
[51] R. W. A. A. De Doncker, D. M. DIVan, and M.
H. Kheraluwala`A three-Phase soft-SWitched
hlgh-POWer-density DC/DC converter for high-
POWer aPPlications:/E 77S. /nd App , VO1
27, nO. 1, pP. 63-73, Jan./Feb. 199l.
[52] Z. Wang and H. Li, A soft switching three-
Phase currenfed bldirectional dc-dc conver
er with high efficlenCy OVer a Wide input volt-
age range,7ns P0erEIectOn , VOl. 27,
no. 2, PP. 669-684, Feb. 2012.
[53] J Hiltunen, V Vaisanen, and P. Sllventoinen, A
bldirectional currened resonant push-Pu=
COnVerter for low voltage, high current appl
CatlOrlS,n Proc 2013Eney Conuers/On
Cbngr Expos!t/On, Sept. 15-19, 2013, PP. 4770-
4774.
54] G. SplaZZi and S Buso, `Analysis of the lnter-
leaved isolated boost converter with coupled
inductors:7ns hd EIeclron , VOl. 62,
no. 7, PP 4481-449l, July2015
551 Proxhima. Online]. Available: http.//www
PrOXhima.com
56] N. Femla, G. Petrone, G. SpagnuoIo, and M.
Vitelll, Pou)er EIecJromCSOnd Con!ro/ 7h-
mqueS forMoxlmumergyHaruesg m Pho-
[ooI[aC fys[ems, Boca Raton, FL; CRC Press,
2013
[57] P M Spaziante, Novel design and non-COn-
VentlOnal appllCations for vanadium redox
technology:presented at the !nternational Re-
dox FIow Battery Forum, Viema, ustrla, June
15-16, 2010
tegenBidings

Of the Future
tybenuare, DeLeaied
and Haman hemcting

SMART HOME
MILOS MANiC,
KASUN AMARASINGHE,
JUAN . RODRIGUEANDINA,
AND CRAIG RIEGER

ntelligent buildings are quickly becoming

COhesive and integral inhabitants of cyber-

Physical ecosystems. Modem buildings

adapt to intemal and extemal elements and
thrive on eveILincreasing data sources, SuCh
as ubiquitous smart devices and sensors,
While mimicking various approaches previously
known in software, hardware, and bioinspired
SyStemS. This article provides an overview of
intelligent buildings of the future from a range of

PerSPeCtives. It discusses everything from the

PrOSPeCtS Of U.S. and world energy consumption
to insights into the future of inte11igent buildings
based on the latest technoIogical advancements
in U.S. industry and government.

US and Wordnergy
Consumptiom Preditions
The U.S. Department of Energys (DOE9 Energy

Information dministration (EIA) estimates the

Share of total U.S. electricity use by major con-

Suming sectors in 2014 as foIIows: reSidential, 36%;
coImercial, 35%; and industrial, 28% (Figure l)

[1], [2]. In U.S. homes, the single largest use of elec-

tricity is for air-COnditi9ning @ooling), followed by
about 40% of electricity use by washers, dryers,

Dl Oecer /0 /IO.20I6 26I5575

Da/e ofpub/ica/10n. 2I Decebe 20]6

32 1E iNDUSTRIAL EECRONICS IVIAGAZiNEDECEMBER 2016

BugS COnSme 70% othe totaeectty

generatedd 50% of tota! nagas poducton

in the United States

and other appliances. In the commercial sector, lighting accounts for about 19% of energy usage and
is the single largest user of electricity. This is because lighting includes office, institutional, Public,
and government buildings as well as pubIic street lighting. Space and water heating (10%), SPace
COOling (11%), and ventilation (6%) together make up 27% of all electricity used. While electricity
use is projected to grow sIowly, efficiency improvements and new appliance standards are expected
to contribute to sIower future growth. The EIAs `Annual Energy Outlook 2015projected a total U,S.

electricity use growth of less than l% per year from 2014 to 2040 [1].
On the world level, the EI, in its International Energy Outlook 2013,projected that world ener-

gy consumption would increase 56% between 2010 and 2040, from 524 quadrillion to 820 quadrillion
British thermal units [3]. Most of this growth will come from non-Organization for Economic Coop-
eration and Development countries, Where demand is driven by strong economic growth. Renew-
able energy and nuclear power are the worlds fastest-grOWing energy sources, eaCh increasing 2.5%

Per year. However, fossil fuels are expected to continue to supply nearly 80% of the worlds energy
through 2040. Natural gas is the fastest-grOWing fossil fuel, aS global supplies of tight gas, Shale

gas, and coal-bed methane increase.

The industrial sector continues to account for the largest share of delivered energy
COnSumPtion and is projected to consume more than half of global delivered en-
ergy in 2040. Based on current policies and regulations governing fossil fueI
use, global energy-related carbon dioxide emissions are projected to rise
to 45 billion metric tons in 2040, a 46% increase from 2010. Economic
growth in developing nations, fueled by a continued. reliance on
fossil fuels, aCCOuntS for most of the emissions increases.
Buildings consume 70% of the total electricity generated
and 50% of total natural gas production in the United
States [4]. Hence, the potential impact of increasing
energy eciency, While continuing to meet cus-

tomer needs and comfort levels and simultane-

OuSly supporting grid operations, is substantial.

Smart Grids ad SmaHomes

The concept of smart buildings, While typi-
Cally referring to smart homes, Can be easily
extended to all types of buildings aesidential,
COmmerCial, and industrial)-in other words,
Smart Cities (Figure 2). The American Recovery
and Reinvestment ct of 2009 (Recovery cD,

Cited by the DOE, Office of Electricity Delivery

and Energy Reliability (OE), PrOVided the DOE
with US$4.5 billion to modemize the electric
POWer grid and implement Title XIII of the Ener-
gy Independence and Security Act of 2007. The
DOE OE was given the lead for modemizing the
more-than-a-Century-Old U.S. electric grid that
Currently consists of more than 9,200 electric-
ity-generating units, With over l million MW of
generating capacity connected to more than
300,000 mi of transmission lines.
The concept of the original one-Way COm-
munication and localized-generation-tO-home

DECEMBER 2016iEEE INDUSIRiAEEarRONiCS MINE35

 llevjsions and Befrigerators and Heating Computerand EiectrochemicaI
ReIated Equipment Freezers 6%Reiated Equipment Processes
7%9% 7% 8%

(a) (b) (C)

Source: EiA, Annuai Energy Source: EIA, Annuai Energy Source: EiA, Manufacturing Energy
Outiook 201 5, Reference Case, Out10Ok 201 5, Reference Case, Consumption Survey 2010
Table 5 (Aprii 2015) labie 5 (Aprii 2015)

FiGURE l - ,S. electicity consumption in 2014 in the (a) esidentiai, (b) commeCiai, and O manufactuing sectos [1] (Coutesy of EiA.)

FiGURE 2 - A smat grid. (images courtesy of and adapted from SmartGid.gov.)

COmmunication concept has evoIved more ecient, SeCure, reliable, and generation and usage. The distribItiorz
toward two-Way electricity and infor- green, aCCOrding to SmartGrid.gov, a intelence (a term coined by the DOE

mation exchange between utilities
and their customers, Offering unprec-
edented levels of consumer participa-
tion and thus creating the essence of
the modem smart grid. The develop-
ing symbiosis of communications, COn-
troIs, and automation makes the grid
DOE information gateway. One of the
Pivota=deas of the smart grid para-
digm is distributed generation, With
microgrids relying on typically renew-
able energy sources such as hydro, bio-
mass, SOIar, Wind, and geothermal, the
COnCePt enabling autonomous power
OE) enables inteIligent and automatic
COntrOIs leading to self-healing and re-
Silience to both malicious and benign
failures. Buildings, eStimated to be re-
SPOnSible for about 40% of all energy
used in the United States, Play a pivotal
role in smart grids.
lntera`tiveness of Buiidings
and Smart Grids
One of the key elements of smart grid
technoIogies is the interactive rela-
tionship between grid operators, utili-
ties, and consumers, Smart grids can
be viewed as interconnected resourc-
es and consumers of energy, With
buildings as major entities of the equa-
tion [mainly because of central hea
ing ventilation and air-COnditioning
(HVAC) and lighting]. Hence, buildings
Play roles in both energy usage and as
energy generation entities avith stor-
age capabilities). Through interaction
With smart grids, Smart buildings @s
building blocks of smart cities [5], [6])
Can Perform load reduction and peak
Shaving (reducing demand for electric-
ity during peak usage time?) and load
Shifting, and can reduce blackouts (to-
ta=oss of powe) and brownouts (volt-
age drops). The concept of islanding in
microgrids can be reduced to the level
Of buildings, Where one or several of
them can share distributed resources
frequently integrated with distributed
energy storage systems. Examples of
distributed resources can entail re-
newables Guch as rooftop solar, Small
turbine/wind, and hydro projectS) and
lately natural gas-based home fuel-Cell
SyStemS, Whereas distributed energy
StOrage SyStemS for buildings entail
water tanks. VionX Energy, a US$12
million DOE National Energy Tt:Chnol-
Ogy Laboratory project scheduled to
be completed in 2018, aims at demon-
Strating competitively priced, multi-
megawatt, 6-10-h operation, 20-year
OPeration lifetime vanadium redox
battery energy storage systems [7].
Johnson ControIs LlOOO In-Building
Distributed Energy Storage System
features 40-65-kWh storage capac-
ity increments of lithium-ion (Li-ion)
Cylindrical batteries with 20-year life
expectancy [8]. Another aspect of
distributed load and generation are
Plug-in electric vehides (PEVS). In the
future, PEVs wi11 serve as distributed
SOurCeS Of stored energy that can put
POWer back into the grid, a COnCePt
Called L,ehCle Jo grid [9]. As mobile
energy storage devices, PEVs have
the potential to inject additional power
into the grid at critical peak times and
-----
e0
"
es S sea, 0
s-0e0s, Ses.
gS ki
also to help integrate variable renew- Simply referred to as s (Sam-
e
r
able power sources into the grid, Which Sungs home monitori
With adequate financial incentives can aptly named Sma[7n they are
accelerate their market penetration. quickly entering the con mer world.
Gartner Analytics predi a30% in-
Cometivity (Sart = Come`ted
AnaltiS)
Another key concept of smart build-
ings is connectivity In fact, in acontext 2020 (Figure 3).
Of smart buildings and smart devices,
the words smar[ and connec[ed are est energy consumers in b ngS, are
being frequently and interchange- being highly modemized ugh the
ably used to denote Intemet of Things Penetration of IoT device The key is-
(Ic/) devices. However, Certain dis-
tinctions need to be made, The mean-
ing of comected is typically reflected
by the ability of buildings to commu- 1
nicate with other buiIdings, With the doing at what time. IoT devices pro-
grid (for reasons of scheduIing, island-
ing, and peak shaving), With utilities,
With energy storage unitsater tanks
for hot or cold energy storage and tht hV nt Xistd bfr, Th
batteries), With occupants (through
COmfort input by means o=ight, air,
heat, and cooling control?), With other
Smart devices (thermostats and sen-
St
O=uture behavior.
SOrS), and so on. In other words, for
the unit to be smart, it needs to be based on several attract e features:
COnneCted @.g., a thermostat needs to COnVenience (e.g., remOt OntrOl and
know about its environment through
an outside weather station or in-home
usage pattems from sensor;). On the
Other hand, COnneCted does not nec-
essarily imply smart. For example, the
trol @utonomousntelli
and prediction of user
terns, and smart scheduli
nt learning
havior pat-
and the
motion sensor may not be smart even ability to control and imp Ve energy
though it is connected to the thermo- efficiency. Comectivity is underly-
Stat, but the thermostat has to be con-
nected for it to depIoy learning and
Prediction algorithms. Remote access
alone does not imply smart aspects
Of devices.
IoT devices feature intelligent algo-
rithms and are constantly increasing
in local processing power. They oper- food expiration dates, nOify users of
ate interactively and autonomously food that needs restocki
While being wirelessly networked
with other such devices or connected
to the Internet directly. Sometimes
DECEMBER 2016 EEE -NUSTR-AEECTRON MAGAZNE 35
 .>zzSPuOU=S-D
u>
u>i
PPd
u
SS
Ee
qPuSpu
Su
uquO< S
d$
pON
uOEOu<
S.
uSS

<
8u

Nest, Samsung, Sleep Number, and
Others improve quality of life and per-
SOnal health, One Of the major benefits
is energy efficiency, energy Savings,
and peak shaving, Starting with such
Simple tasks as deferring refrigera-
tor defrost cydes or dishwasher and
laundry deferral untiI off-Peak hours
[10, [11].
Theskyis the limit when it comes to
energy efficiency and smart devices to-
day. Windows, doors, and skylights can
gain and lose heat through conduction
(U-factor) or radiation (Solar heat gain
COefficienO. In 1990 alone, the energy
used to offset unwanted heat losses
and gains through windows in residen-
tial and commercial buildings cost the
United States US$20 billion (One-fourth
Of all the energy used for space heat-
ing and cooling) [12]. Smart windows,
Smart glass, Or SWitchable glass use
the technoIogy called s[ISpended po
ticle deices (SPD9 [13], adjusting ac
VOltage to the SPD film to quickly con-
trol the amount of light, glare, and heat
PaSSing through windows, Rayno win-
dows use the polymer-dispersed liquid
CryStal technoIogy, Which combines
POlymers and liquid crystal materials
to control transparency [14], [15]. Be-
Sides their use for energy efficiency,
these technoIogies can be used in
Smart buildings for instant privacy, tO
eliminate the need for curtains, tO filter
ultraviolet rays, Or aS a rear-PrOjection
Surface for theaters or high-PrOfile cor-
POrate and retail displays,
Various manufacturers provide
automation and energy-efficiency
COntrOIs. Companies like Lutron, Hon-
eywell, and Johnson ControIs provide
SOlutions ranging from commercial
Smart grid, Whole building, and resi-
dential solutions for energy efficiency.
Lutrons Quantum lighting controand
energy management system offers a
Smart decision for any building own-
erin terms of scheduling of lights
and lowering shades for energy sav-
ings and also for the comfort, Safety,
and security of occupants. Quantum
and EcoSystem solutions enable shed-
ding of a percentage of a buildings
lighting output during peak demand,
instantly saving energy. The solutions
also provide control, COnfiguration,
e deveoping sybiosis oconications
CO0s, andtomationakes the grid mor
ecieSere, eabe, and gee
monitoring, and reporting on the and smart lock;) or larg' @.g., large
lighting for any space in a building for energy storage batteries ld electric
maximum energy efficiency, COmfort, Car?). As highly integra d as they
and productivity [16]. are, SuCh systems run hi( l eXPOSure
An example of such concepts is so- risks. The same informati l flow that
Called doylight zJtOnOmy, a SuStain- enables users and mana!
able concept driven by Lutron that building complexes and idential
adapts to its environment and claims home users to monitor Of COntrOl
large
reducing daytime lighting energy
use by 65% or more through the use
Of automated shades [16]. Designing
for daylight autonomy invoIves un-
derstanding how the entire building ample, mOnitoring occu
is affected by the dynamic nature of Can tell when a person es home,
daylight and creating a lighting con-
troI strategy to automatically adjust
to these changes.
Securit and Resiliene
Of lmtelligemt Buildings
If intelligent buildings are the future, Cal infrastructure),
then so too are cyberthreats to build- In the world of home
ing services [17]. According to Grand
View Research, a San Francisco-based
the security research firm
COnSulting firm, the inteIligent build-
ing automation technoIogies market is devices, eValuating sim featu res
expected to reach US$98,95 billion by SuCh as the encryption of
2024 [18]. The technoIogy is expected
to grow rapidly due to benefits such as
increased energy efficiency, OCCuPant
COmfort, and productivity as we11 as
Seamless operation of HVAC, electric-
ity, lighting, and other systems. Fur- forms. In addition to pote al software
thermore, the increasing demand for exploitation, SuCh devices Suffer from
SeCurity and life safety systems (e.g.,
SyStemS that indicate the presence
hardware security issue
Physical access @ univers hrough
;erial-bus
Of firO in education, hospitality, and booD, an attaCker can root ac-
large commercial complexes is ex- CeSS, aS Shown in 2014 Si m ilarly,
PeCted to give a boost to the adoption
Of intelligent buildings automaLtion.
Modern buildings heavily rely on
Femandes et al, Publish
May 2016
two intrinsic design flaws ih Samsungs
SmartThings: 55% of app
SeVeral advantageous concepts: in- Privileged (given excessi
teroperability, COmeCtivity, doud ser-
;
Vices, remOte mOnitoring and control,
Or PrOgrammable logic contro11ers. t On the enterprise le the risks
the heart of all these are the communi- grow higher. One sim ) PrOblem
Cations among sensors, hubs, and nu- is the introduction of IoT de-
merous smart devices, Whether smaIl vices into a network. exfiltra-
@.g., COffee machines, POWer Outlets, tion through any devic built-in
E.EMBER 216,US,R,ARN,CAZ,NE 3,

VAa ing systS. tgSt nrgy able (known as plfor fIee tt)OrsO. To
COS rsn bugs, are beig higy modenized
o Penetration o=odevices necessary cost for the resilience of mis-
network co a Department of Homeland Security
and requir( alert [22].
munications (e.g., if a SoIutions in this area need to take
Smart rer into account various approaches. One
Payment Ce ZOne) [20]. Another is- is increasing resilience by segmenta-
Sue invoIve tion of the network of connected de-
application Vices (1imiting the exposur ), COuPled
With the use of strong user/PaSSWOrd
the netw Can PrOPerly handle in-
COmbinations. CIoud-hosted systems
relieve customers of the burden of se-
fluxes in volume of data, An ad- Curing sensitive data and web services.
ditional i the legality of storing Geographically separated redundancy
t hJ e r
increases resilience in case of cata-
U.S. Federal Bureau StrOPhic events at data centers in one
reported a memo on location. Cloud services must include
into the heating and multifactor authentication via various
ng system of a New PrOOfs of identity-SOmething that us-
COmPany. Widely re- ers know, through a password; SOme-
thing they possess, aS With a phone;
and something inherent to them, aS
With fingerprints [23]. In addition to
the best cybersecurity practices be-
ing made an integral part of the de-
PIoyment of equipment and training
for building managers, COntingency
themselves
Plans should be drawn up for periods
during which intelligence is not avail-
maintain minimum acceptable levels of
SerVice, hardwired hardware may be a
ion-Critical building automation sys-
tems, eVen at a COSt Of sacrificing the
intelligent part of the automation 7].
Resilience-a SyStems ability to
bounce back after malicious or benign
failures or, from a business perspec-
tive, the ability to maLintain continuity
Of business operations-aSSumeS an
intelligent response that goes beyond
fault tolerance and is inextricably
linked with cybersecurity [24]. The da-
ta-driven techniques overviewed in the
following, SOmetimes referred to aso-
inspired, Selhealing, and recovring,
represent an integral component of
resiIience. The interactiveness and
interoperability of modem buildings,
along with the ubiquitous IoT devices
that generate large data streams, also
bring bioinspired data mining and data
analytics into the purview of resilience
in the domain ontelligent buildings.
Atiicia nteigene
in Buildings
e Need foreene
Due to the interactive, adaptive, and in-
terconnected nature of buildings, their
COmPOnentS, and outside environments,
modern buildings must be capable of
negotiating constantly changing scenar
ios. Continuous communications among
Smart hubs, SenSOrS, and appliances
Within buildings as well as communica-
tions among smart meters, reneWable
energy generators, StOrage units, and
utiIities generate massive, heterogeneous
data sets about every aspect of their op-
erations. These big data sets require
increasingly automated and adaptive ap-
PrOaChes to information processing and
reaI-time decision making.
Artificial intelligence @I) and ma-
Chine learning (ML) techniques ex-
hibit proven capabilities for leaming
from heterogeneous data sets [25].
Such techniques can identify pattems
Or trends that exist in data and extract
CruCial performance knowledge, make
accurate predictions of future system
StateS, and identify anomalous scenar-
ios that may lead to suboptimal behav-
ior due to benign or malicious faults.
These approaches can be effectively
used for tasks ranging from building
energy management and energy effi-
Ciency, Self-healing, and adaptation to
the securitynformation assurance,

and resiliency of such systems.

Brfef OveVfew of A/

AI and ML encompass a multitude of

algorithms and techniques. Tfaditional 1utionized a multitude of such as This section Very brief
techniquessuchasIogisticregression,SPeeChrecognition,natura=anguageintroductiontotraditionaLl ANNsand

artificialneuralnetworks@NN?),fuzzyprocessing,andcomputervisionappli-SeVeraldeepleamingar hitectures:

1ogicsystems(FLS;)(Figure5),SuPPOrtCationssuchasfacerecognition.convolutionalneuralnetwo ks(CNNi),

VeCtOrmachines(SVM?),anddiffer-Deeplearningextendsthecapabili-longshort-termmemOr (LSTM),

entBayesianprobabilisticmodelsaretiesofstandardANNsbyenablingar-andrestrictedBoltzman machines

We11-documentedmethodsandhavechitecturesofmanylayers.Therefore,(RBMi).Thesealgorithms reselected

beenextensivelyusedinawidearraydeepleamingenabIesleamingofcom-Sincetheyarerelevanttot econcrete

Ofdomainsforleamingpattemsandplexpattemsthatexistindatathroughapplicationandcasestudy iscussedin

trendsindata,Recently,theadventofmultiplelayersofabstraction.Thethenextsections"However, tshouldbe

moderndevelopmentofdeeplearn-nOtedthattherearemore deeplearn- ithmsthat

FuzzyLogic naturallyindinedresearcherstoinves-Canbeusedinbuildingene
inganditsrecentwidespreadusehaveingandtraditionalAIalgo gysystems.

Ofintelligentbuildings.ThecapabiIityprehensivereviewofde Pleaming

OfleamingcomplexpattemsusingthetechniquesandmethodoIo ies.

multilayeredarchitectureenablesdeepANNsareAIarchitect resbased

learningalgorithmstoextractpatternsonbioIogicalneuralnet Orks(See
Fuzzy tigateitseffectivenessinthedomainReadersarereferredto[26
andtrendsfromgrowinganddiverseFigure6).Asinthelatte
foracom-
,thebasic

Ruies datastreamsofintelligentbuildingsunitofanNNisaneuron. bioIogical

Ofthefuture.Therefore,throughneuronproducesanoutp tbycom-

FiGJRE5-FLS[35].theeffectiveuseofdeeplearning,theparingaweightedsumof lnPutStOa

Axon utput ayer

(Ac tivationFunction)
HiddenHidden

s,/LayerLayer2
x

X2W2output ;1y lnputsxsummatinfWightdInptS+1+1+1

XnandA CtivationFunction
Wb

+1

FIGJRE6-AnANNachitectue[35L MAGAZiNE39
threshold.
ics the bi neuron through a
Similar methodoIogy of using weights
and a thr Old value to produce an
l rithms, introduced by Hochreiter and
rorlS is arranged to produce
given an input vec-
nnected network has
leaming the interde-
Ween the inputs and
Well-trained ANN has
ltS for inputs it has not
lSt. ANNs are we11 docu-
roven for being useful in
ions,
a special type of neural
network anq are mainly used to process
topoIogy (Figure 7) [29].
The CNN ning process is a great ex-
ample of deep learning algorithms
learn thr layers of abstraction. As
tence of a erent feature. Hence, When
Put tOgethet, CNN layers have the capa-
bility of le ing very complex patterns
and trend data. Figure 7 shows the
arch itectu r Of a standard CNN. CNNs
have been hown to be extremely use-
fu=n fields SuCh as computer vision,
Functions of a Convolutional Layer (Expanded)
NN aChitecture [28].
image classification, and time series
data modeling.
LSTMs and RBMs are increasingly
used in the literature as generative
deep leaming algorithms. LSTM algo-
tanks [34], and/Or reneWable energy
Schmidhuber [30], are a tyPe Of recur-
rent neural network (RNN) composed
Of memory cells with self-COnneCtions.
Figure 8 shows an LSTM architecture
With multiple LSTM cells. These can
be stacked in a multiIayer architecture
to create a deep network. LSTMs have
been shown to be extremely useful in
generative models, eSPeCia11y in the
natura=anguage processing domain.
RBMs [31] are shallow two-layer neural
networks. The first layer of an RBM is
Called the L)isib[e /qyer and the second
is thedden /qyer RBMs can learn fea-
tures that exist in data in an unsuper-
Vised fashion. Therefore, they do not
need preamotated data to leam the
features. RBMs are the building blocks
Of deep belief networks (DBNi) [32]
and have been used in a range of do-
mains, including image processing and
time series data modeling.
Concree Appat;on ofA/: De ual building-level energy forecasting
Leaming-Based Loademd
eCOng h Bu()gS response locally [33]. In other words,
Load/demand forecasting is predict-
ing the energy consumption of an indi-
Vidual building or an aggregate, SuCh
as a city or a county, for a future time
SteP. Accurate load forecasts are ex-
tremely beneficial for decision making
at the grid level as well as at the in-
dividual building level [33]. Modern
building design is heading in a direc-
tion to incorporate energy storage de-
Vices, SuCh as thermal energy storage
generators, SuCh as photovoltaics or
Windmills. Thus, Smart buildings will
have to make decisions on what pro-
POrtions of utility energy, StOred en-
ergy, and locally generated energy to
use to attain optimal energy eficiency
[35], Therefore, at the building level,
accurate energy load forecasting helps
make building-level decisions, SuCh
as optima=ocal energy storage con-
trol [34] or renewable energy control.
From a grid perspective, Smart grids
have to optimally utilize the various
energy sources, including renewables
[36]. Smart grids promise an unprec-
edented level of flexibility in energy
management, making power genera-
tion and distribution more efficient
and minimizing energy waste [33],
[38], [39]. Therefore, at the grid level,
accurate future predictions of individ-
ual demand help the grid adapt to the
Variable demand, and having individ-
helps the grid carry out the demand
local demand can be met with locaI
distribution, Which leads to more e
ficient energy transmission and distr
bution. Therefore, it can be seen that
demand prediction can be discussed
from an aggregate standpoint and an
Fu=y
ConvoiutionaI Connected
Laye Laye r(S)
individual standpoint. Howevern
the interest of brevity and of remain-
ing consistent with the theme of this
article, the discussion in this section
is focused on recent developments in
building-leve=oad forecasting.
Load forecasting can be classified
into three classes: 1) short-term load
forecasting, 2) medium-term load fore-
CaSting, and 3) long-term load forecast-
ing [33], [39]. Regardless of the type of
forecasting, tO aCCurately predict ener-
gy consumption, the forecasting meth-
OdoIogy should be able to accurately
model the dependencies between build-
ing factors and energy consumption. Re-
SearCh has shown that load forecasting
is an extremely difficult problem [33],
[40]. Hence, a range Of methods-Phys-
ics principles-based and statistics and
AI based-have been proposed in the
literature. This articIe focuses on the
recent advancements in AI-based build-
ing-leve1 1oad forecasting.
One of the most recent advances
in building-leve=oad forecasting has
been the introduction of deep learn-
ing into the domain. Several recent e
forts exist in the literature that inves-
tigate and prove the effectiveness of
using deep learning techniques over
traditional techniques. Mocanu et al.
tested two variations of the RBM: the
factored conditional RBM (FCRBM)
and the conditional RBM (CRBM)
[33]. In the study, the CRBM and the
FCRBM were compared to the NN,
SVM, and RNN. The aLuthors conclud-
ed that the FCRBM outperforms all the
Other methods.
In another study, DBNs, Which are
architectures built with layered RBMs,
Were uSed for electricity load fore-
CaSting by Dedinec et al. [41]. The au-
thors concluded that the DBN-based
method outperforms traditional ANNs.
Qiu et al. used an ensemble of DBNs
COuPled with a traditional SVM-based
regression technique [42] The authors
Showed that the presented ensemble
DBN method outperforms methods
SuCh as ANN, SVM, and even single DBN
for the data set it was tested on. There-
fore, it can be seen that deep leaming
techniques have shown promise in im-
PrOVing the performance o=oad-fore-
CaSting methodoIogies and hence have
Deepeaming has revolutioized altitude of
fields SuCh as speech recognition, natuaa guage
PrOCeSSing, and face recognition
the potential of having a significant im- residential energy con umer. The
PaCt On the smart grids, Smart homes, Same data set that was uSed in [33]
and smart cities of tomorrow Next, We
look at a case study conducted by the
authors to compare the performance of Pared to the FCRBM met . Further-
deep leaming techniques. more, tO keep the tests form. the
Same training and testin data were
Case Study: Compahson of Deap used as in [33].
Leamhg Aohms for Demond
forecasfg h Bui/di/)gS Data Set
s mentioned, deep learning method- The data set contains el(
OIogies have been shown to be ben-
eficial in the domain of building-level
demand forecasting. However, the
Published studies lack compara-
tive analyses among deep learning
techniques. The presented case tudy
discusses the work conducted by the
authors to bridge that gap. In this
WOrk, We discuss the effectiveness of training data and th
deep leaming-based demand forecast- used as testing data,
ing using three deep learning architec- tectures, the electricit
tures implemented on the same data forthe next 60 hwas pr
Set. The architectures were: Figure 9-(o illust
the standard LSTM-based load abiIity present in the
forecasting architecture ure 9(shows the
the LSTM-based Sequence-tO-Se- COnSumPtion across
quence architecture (LSTM S2S)
the CNN-based architecture.
All three architectures were tested
On a benchmark data set for a single
O-1]iLSMCii y(t)
f(02)
02
X
LSTM
I 0[ SigmOidForgetGatel i (t,d q -11 Layer2
t) 01
[mOidEmOid LSTM Layerl
_-,,t ]
(a) (b)
F-GURE 8 (a) An LSTM ce-i and (b) a mu-tiIaye LSTM netwo9].l
..EMBER 2,6,NR.A=..C,RN,MAAZ,N. ,,
 the previous step and time stamp data
are fed into the model. Table l lists
1.2 the time stamp data used as inputs to
$3,500 3,000 2,500 .1 a11 three models. The output from the
LSTM network is the predicted power
08
COnSumPtion for the next time step.
Tb predict further into the future, the

06
0.4
02 Prediction of the next time step can be
0 0 2,2 2
1,8 0 used. The mode=s trained using the
Standard backpropagation through
time (BPTT) method [44] with gradient
Time(Months)Time(Day)
descent. For the elaborated methodo
(a)(b) e-Mon. ee. e-Wed. --hu. Fi.
Ogy, readers are referred to [39].

LSTM-Based S2S Achitecture

for Load Forecasting

"6 ) . .
S2S architectures for neural networks
Were PrOPOSed by Sutskever et al. [45]
as a method of mapping sequences of
arbitrary lengths. The LSTM S2S archi-
tecture for load forecasting contains
two standard LSTM networks, namely,
1 the encoder and decoder. The objec-
0.8 0.2 0 - iiii tive of the encoder is to convert input
SequenCeS Of variable length into a

Predefined, fixed-length vector. This

fixed-length vector is then used as the
input for the decoder. The decoder

PrOduces the output vector, Which is

23456789101112131415161718192021222324 the energy load forecast for the next
Tjme(HourofDay) n steps, This architecture enables in-
(C)
PutS Of arbitrary length. In the energy
load forecasting context, this means
FIGURE9 - (a) e monthly energy use [46]. (b) The enegy use pe day ofthe week [46]. (C) The
Change in ene use pe hour pedayoftheweek [46]. that an arbitrary number of historical
energy consumption data can be fed

l-H

I STAMPINPUTSFORTHEDpEARNINGALCORITHMS,
into the architecture as inputs. The
encoder network is trained alone as
a preprocessing step, uSing the same
methodoIogy mentioned in the stan-
INPUTVARIAB DESCRIPTION VAUS
dard LSTM method. Then the encoder
Houoftheday HourofthedayfoJthefirstpediction [1,24] is plugged to the decoder, and both
networks are trained together using
Month Monthofthefistpediction [1,12!
BPTT. For the eIaborated methodol-
DyOftheweek Dayoftheweekfothefistprediction [17]
Ogy, readers are referred to [39].
DyOfthemont Dayofthemonthfo=hefirstpediction Il,]

Weekendfiag aVerageen rgy Flagthatissetifthedayofthefistpedictionisaweekend COnSumPtionacrossFurthermore,itshows IO,1] thattheweek- CNN-Based Load Forecasting
Time series energy consumption
data are viewed as a one-dimensional

grid. To perform the CNN-based en-

thesevend,ySOftheweek.Itcanbedaysshowasimilarusepatternwhile ergy prediction, the CNN is fed with
tht th! wknd has higher en-Weekends are derent. a predefined number of historicaI
Ption compared to the energy consumption data. Only the
Weekdays. igure 9 illustrates the Standard LSTM-BasedOad Foecasting historical consumption data are fed
Variability f energy use across the The standard LSTM algorithm was into the convolutiona=ayers. The
hours of tergyCOnS day for the seven days used as the first architecture to per time stamp data are not used in this
of th Wk. A signifi.ant vrin fm th building-levI ele.tiityld Phase. Once the historical energy
in us r!s th 24 h n b Sn. frSt.Thl.trilnSumPtinf COnSumPtion data are subjected to

42 INDUSEECTRONICS MAGAZ-NEDECEMBER 2O16

the convolution and pooling phases,
the output is fed into a fully con-
Mechanisms shoud exist fohumans to interatt
nected network. Time stamp data are
introduced into the system at this Wad provide feedback to the buildng
Phase. The training of the architec-
anageent system`
ture is carried out using BPTT with
a gradient descent model. For the
elaborated methodoIogy, readers are
referred to [46]. Significant portion of occupants are the occupants plays a sigpificant role
still left dissatisfied with the comfort in energy consumption land green-
ExperimentaI ResuIts PrOVided by building thermal condi- house gas emissions [47]. Occupant
As mentioned, a11 three architectures tions [47]. Hence, it is evident that behavior is a combination of human
were tested on the benchmark data mechanisms should exist for humans activity and preferencesl [50]. Occu-
Set On the single residential customer, to interact with and provide feedback PantS thus have a huge impact on a
With an identical training/testing split. to the building management system. buildings energy demand. Therefore,

Figure lO shows a sample prediction Humans in the building can be divid- the human element from the perspec-
obtained from the standard LSTM. It ed into two main categories: 1) occu- tive of the occupants shod be taken

can be observed that the LSTM is able PantS Or uSerS Of the building and 2) into consideration on the following
to follow the general trend of the pre- building managers. The behavior of two fronts to optimize d buildings

diction. However, it can be seen that the

LSTM fails to adapt to certain changes.
Figure ll shows a sampIe prediction i

PrOduced by the S2S architecture. It

can be observed that the S2S model
5 4 3 2 1 0 !i 0
manages to estimate the rapid chang-
es that appear in the data. Figure 12
Shows a sample CNN prediction. It can
be seen that the CNN performs in a
similar fashion. A standard ANN was
implemented on the same data set,
and the prediction was carried out for
the purpose of comparison. Figure 13
Shows a sampIeANN prediction. Table 2
PreSentS the average prediction errors
204060801001
in terms of root-mean-Square-errOr Val-
Time(Hours)
ues obtained for the three deep learn-
ing architectures and the ANN. It can
FiGURE lO - The prediction esuits forthe standad LSTM [39].
be seen that all three deep leaming
architectures outperformed standard
ANNs for the tested data set. Further-
more, it can be seen that all three
deep leaming architectures produced
4.0 3.5 30 15 1.0 0.5 0,0 0
results comparable to each other and
also comparable to [46].

Buildings and Huans

As discussed before, elements such
a COnneCtivity and AI are essen-

tial for achieving energy-efficient

and smart buildings and the cities
Of the future. However, While those
elements play a huge role in er)ergy
efficiency, anOther important aspect
Of buildings is ensuring occupant 020406080100 12
COmfort [34], [47]-[49]. Even with the Time(Hours)
recent advances in inte11igent controI
SChemes, it has been shown that a FGURE = - The pediction esuits fo the LSTM-based S2S [39].

DECEMB2016iE INDUSTRIAEECTRONIC? MAGAZiNE43

 ) --X--ReaiMeasurement energy usage while maintaining occu-

Pant COmfort:
mOdeling occupant activity

enabling personalized comfort feed-

back and mechanisms to optimally
i
incorporate subjective comfort feed-
3 2 < 1 4 ( [; "; -CNNEstimation
back.
In addition to the occupants, from
a building managers perspective, au-

tomated building controIs can be sup-

Plemented with human-in-the-loop,

Semiautomated controI strategies.
Such strategies have the capability of
using the knowledge of an experienced
building manager to supplement the
intelligent controI schemes in place.

0102030405060
Human-Buing /ntemcfron for
Time(Hours)
Comfortdey Efenay
While data-driven intelligent algo-
FIGURE 12 - The pediction esuIts fo the CNN [46]. rithms can provide contro=or in-
CreaSed energy efficiency, balancing

Performance with occupant comfort

invoIves acquiring data at the individ-
ual workstation level. However, Cur-
rent building energy-SyStem designs
lack the implementation of sensors at
4 i.: --ReaIMeasuement
individual work locations. Therefore,
l these systems are dependent upon ag-
l
l gregate or zone understanding of the

l )l l i ll l ParameterS for achieving individual

COmfort. Individual occupant feedback
is extremely important for maintain-
2 15 1 05 0 O-ANNEstimation ing comfort levels because human
COmfort is subjective. Accurately un-
derstanding the impact on individuals
and variables such as radiation from
Windows or inaLdequate airflow is of
the essence, eSPeCially since those
factors are subjective. Therefore, the
unavailability of highly granular in-
01020304050
ime(Hours)
formation for the entire buiIding may
Iead to areas of low comfort and low
energy dissipation going unnoticed.
FIGURE 13 - The pediction esuIts for the ANN [46], To alleviate this, aL method of acquiring
individual comfort feedback is neces-
Sary. Therefore, methods need to ex-
ist that enable direct communication
between occupants and the building

PREDICiONRORS FOR THE TESTMETHODOOGIES (RMSE). energy management system (BEMS).

Human-COmPuter interaction meth-
TRAiNiNG ERROR (RMSETEST!NG ERROR (RMSE
Odologies should be incorporated to
0 72

PrOVide easy-tO-aCCeSS and intuitive

interfaces for occupants to send their
COmfort-level feedback to the BEMS.
While automating building con-
trol is crucial for achieving building
energy efficiency, it is difficult to ig-
nore the impact that an experienced
VISua =Za [OniyPeAHU-LeVe VI eWOneSl
building manager can make in opti-
mizing and supplementing the auto-
mated controI. For this to be possible, Anoma-ylndfatOrLeW F, l
it is imperative to have an apI)rOPriate il
interface between the human manager :: -: (Ia
:i+ i} =! =;
and the controI system. The interface
- [
Should be able to provide the building

manager with data streams from dif-

Ction =ty S /-:-- ; l
ferent building sensors (information
7
PrOCeSSing being an essential task : l
in automation [51]) and information
about the controI system. In addition,
1 r

the interface should be able to provide l . i 1

the manager with information about .___ l

the control actions in real time. ends

LingisticsmmaryofSe ectedAnomai eS Dat

Case Stu(m-Machhe
eCnrO)g O FIGURE 14 - The inteface of the deveioped tooI fo incopoating the building manager

Human E/emenf (Windows and Andoid Versions).

The main objective of the performed

Study was to devise strategies to in-
COrPOrate the human in the building
automation and control to increase
energy efficiency and occupant com-
fort. Two types of human interaction
With the building and the BEMS were
identified: 1) by building managers
and 2) by building occupants. There-
fore, Strategies were developed to in-
COrPOrate human interaction with the
BEMS using two different methods: 1)
incorporating expert control through
building managers to supplement the
automated control for increased en-
ergy efficiency and 2) incorporating
OCCuPant feedback for increasing oc-
CuPant COmfort.

Building Mnage inteaction

A user-friendly visualization tooI was

developed that presents a real-time
data stream from sensors, anOmaIies
in the data streams, and linguistic sum-
maries of the data. nomalies in the
data are identified using an AI-based
framework [52]. In the anomaly detec-
tion process, AI-based data-mining al-
gorithms extract and model the normal
FIGURE 15 - The webeface of the building manage tool"
using human-interpretable linguistic
terms. Therefore, a Summary Of data
trends pertaining to building perfor-
mance is given to the building manger
in an understandable manner. Both
AI-based frameworks were developed
The visualization tooI was devel-
OPed for different platforms. First,
the interface was developed for a Mi-
CrOSOft Windows-based platform. Tb
PrOVide mobile capability, the inter-
face was developed as an ndroid ap-

behavior of the building and thus are
CaPable odentifying behavior that
is anomalous and potentially harm-
ful. Similarly, linguistic summaries of
data are generated using an AI-based
framework [52]. In this framework, the
data from the building are summarized
by the authors. However, those frame-
WOrks are out of the scope of this ar-
ticle. The developed visualization tool
focuses on increasing the building
managers situational awareness by
PrOViding a comprehensive overview
Of building performance.
plication. The functionality was kept
identical across the two versions.
Figure 14 shows the interface for the
Windows and the Android versions.
Furthermore, the tooI was extend-
ed to a web-based version to make
it platform independent. Figure 15

Bdings wi conue theevoio
toward becoingnd baing
Cybehysicamechisms
Shows the interface for the web-
based appIication.
The tooI was designed to be inter-
active so the user would be able to se-
lect different information to visualize.
Furthermore, the user is able to use
the tool to update the anomaly detec-
tion algorithm. That is, the building
manager is able to provide feedback
On the detected anomalies. For ex-
ampIe, the building manager is given
the capability of validating a detected
anomaly" If the detected anomaly is
a false positive, the anomaly detec-
tion algorithm wil=earn that and will
refrain from tagging that behavior as
an anomaly thereafter. Therefore, the
knowledge of the experienced build-
ing manager is incorporated in the
building automation through the de-
Veloped interface.
Occupant Interaction
Implementing an extensive sensor
network to achieve individual work-
Station thermal environments is
time consuming and entails a signifi-
Cant financial commitment. There-
fore, the cost-effective and feasible
method of acquiring the required
data is a user-Centered approach. A
user-Centered approach will ease
the task of building managers and
the automated building controller to
PrOaCtively monitor occupantscom-
fort levels and adjust building states
FiGURE 16 - The deveioped modulr Wieless senso.
46 iE INDUSTRELECTRONICS MAGAZiNEDECEMBER 2016
at their specific Iocation. Once the
from the occupants, the imprecise
for optimal comfort and efficiency
through the interface elaborated in
the section above.
Therefore, a uSer-Centric data col-
1ection methodoIogy was developed
to acquire highly granuIar readings
Of the ambient environmental condi_
tions in buildings and the subjective
COmfort levels of users. To acquire
highly granular recordings of ambient
environmental conditions in the build-
ing, a Iow-COSt SenSOr WaS developed
[53] The sensor has a modular design
SO that new components can be added
to it without much effort [53]. The de-
Signed sensor includes measurements
SuCh as temperature, humidity, CO2,
and visible light. Figure 16 shows the
designed sensor.
Even though depIoying sensors
at individual workstations can help
Obtain highly granular data, it does
not factor in the subjective human
feedback. The current BEMS systems
lack a methodoIogy for the users to
interact with the building managers.
Therefore, tO PrOVide a method for
the users to interact with the building
COntrOl, a SmartPhone app was de-
Veloped because of the ease of ac-
CeSS and use. Figure 17 shows the
developed smartphone application.
Through the developed comfort app,
the users are able to report back to
the building managers about com-
fort levels in terms of such things as
act in the same way as perspiration to
lighting, temPerature, and ventilation
necessary information is acquired
human feedback is handled in lin_
guistic terms [52]. Then the feed-
back is incorporated in the build-
ing control to improve the comfort
level of the individuaIs.
In addition to reporting comfort
data, uSerS are able to use the mobile
application to report system failures
to the managers. This method can
be used to send specific information
about which system failed, COmmentS
regarding the failure, and even images
Of the failure. This information can be
used with the anomaly detection algo-
rithms mentioned in the previous sec-
tion to provide the building manager
With more information on the subop-
timal behavior of the building, Fur-
thermore, the developed smartphone
application connects to the developed
modular sensor to acquire the data for
localized details.
00king into the Futue
Buildings wi continue their evolution
toward becoming living and breathing
Cyberphysical mechanisms. The U.S.
Green Building Council, under its Lead-
ership in Energy and Efficient Design
PrOgram, may be only the beginning
Of the transition toward the concept
Of living buildings. The Living Building
Challenge certification program that
Started in 2006 continues the promo-
tion and advocacy of sustainability in
the building environment. While net-
ZerO buildings (buildings with zero
net energy consumption, i.e., nOt uSing
more energy then they themselves gen-
eratO are still rare, they may become
more common with advances in renew-
ables and distributed storage technoIo-
gies, SuCh as Li-ion batteries and PEVs.
In the future, buildings with a surplus of
energy may be able to buy and se11 that
energy to the grid or to other buildings.
The concept of living buildings will
likely further the analogy with hu-
man beings. Just as the human body
SWeatS tO release excess heat, build-
ings may use evaporative roof sys-
tems. Rain-absorbing matting could
COOl the buildings as the rain evapo-
rates. Similarly, aS blood vessels
COnStrict or dilate to preserve or re-
lease heat, buildings will be using in-
telligent adaptive insulation systems
and smart transparent windows and
Shading. Although natural breath-
ing systems such as wind towers and
Wind catchers have been used in
buildings for centuries, mOdern tech-
noIogies will enable more effective,
automated, and predictive controIs,
using modern polymers and bioma-
terials (SuCh as sehealing concrete)
and architectures of such structures.
Modern renewables generators, tur-
bine designs, and wind energy towers
Wil=ncrease buildingsautonomy and
building grid islanding.
At the smart grid level, Smart loads
Will interact with utilities to reduce peak
demand or respond to demand dispatch
(increasing loads at times of excess gen-
eration). Grid-interactive hot and cold
thermal energy storage systems (tanks)
Will further advance load shifting and in-
CreaSe the sustainability and autonomy
Of smart buildings. Advanced power
electronics wi11 be able to provide sub-
minute load management [54].
When it comes to human-building
interactions, the increase of modali-
ties and platforms of heterogeneous
FIGJRE 17 - The smartphone appiication and its featues.
th the growth of ubiqoSdevices,Ode
bugs seamteSly iegrate whe environme
oweg eegeated expSeS and ieasg
producty ad the quty ofe
SenSOr SyStemS Wil=ead to the seam-
less integration of buildings into the
everyday live Of humans. The novel
interaction technoIogies emerging
With smart devices via sound, VOice,
and three-dimensional touch wi11 be-
COme a nOrm for communicating with
Smart building components. A home-
owners arrival at his or her house will
trigger preset rules, and the owner
Will be able to ask for the curtains to
be cIosed or the lighting and music ad-
justed. Interesting questions will arise,
SuCh as the personification of smart
building components @s with thera-
Peutic robots like ParD, Or queStions
Of human changes in response to con-
tinuous interactions with buildings.
Software will play an increasing role
in the buildings of the future. Similar
to software virtualization (hard disk
drives or software-defined network?),
the virtualization of power plants that
COmbines geographically dispersed
resources (e.g., Smart homes, local re-
newables, and PEV?) can increase the
COrrelation between resources and en-
able greater flexibility, While decreas-
ing the uncertainty associated with
individual resources used in isolation
[54]. The aggregated resources could
be bid into wholesale electricity mar-
kets and provide other grid services if
allowed. One emerging concept is the
Distributed Energy Resource Manage-
ment System software platform.
I techniques are expected to con-
tinue their way into the buildings of
the future. From automation and occu-
Pant behavioral pattem learning and
Prediction to processing of the big data
generated by buildings and smart grids,
AI techniques have already been estab-
1ished as an approach to the autono-
mous execution of routines on behalf of
users. With regard to energy efficiency
as one of the most important aspects
Of future smart cities, aPPrOaChes such
as deep learning (Googles DeepMind)
Were rePOrted in July of this year to
have cut cooling energy use by 40%
and total energy use by 15% in Googles
data centers.
Con`!usion
This artide presented an overview of
the state of the art and the future of
Smart buildings, Starting with U.S. and
WOrld energy consumption predictions,
We OVerViewed the most important as-
PeCtS Of smart grids and smart build-
ings, elaborating further on the interac-
tiveness and interoperabiIity between
the two. We then discussed the emerg-
ing aspects of smart homes-COnneC-
tivity and analytics-While recognizing
the increasingly evident issues of the
SeCurity and resilience of intelligent
buildings and the corresponding need
for research in these areas. The article
additionally overviewed the cutting-
edge AI techniques, reflecting on the
recent hot topics in deep leaming. AIso
PreSented were the results of case stud-
ies done by the authors on two highIy
relevant problems: load/demand fore-
CaSting for buildings and human-build-
ing interaction. The article concluded
With insights into the future of intelli-
gent buildings.
Modern intelligent buildings are
becoming cohesive cyberphysical
ecosystems that live and breathe with
their surroundings. Intelligent build-
ings adapt to external (ieasonal) and
intemal (OCCuPanCy and usage pat-
tem9 changes and are doing so with
lnCreaSing autonomy and sustainabil-
ity" Modem buildings thrive on data
SOurCeS that were previously nonexis-
tent (!ensor?) or ignored and feature
highly reconfigurable infrastructure
and control elements. With the growth
Of ubiquitous IdT devices, mOdem
buildings seamlessly integrate with the
environment, lowering energy-related
expenses and increasing productivity
and the quality of life,
Biographies
Ms Mic Gnisko@ieee.org) is a
PrOfessor in the Computer Science De-
Partment and director of the Modern
Heuristics Research Group at Virginia
Commonwealth University, Richmond.
He has over 20 years of academic and
industrial experience leading over 30
research grants focusing on computa-
tional intelligence in energy, reSilience,
Cybersecurity, and human-SyStem
interaction in buildings and critical
infrastructures. He is a cofounder of
the IEEE Ttchnical Committee on Re-
Silience and Security in Industry. He
has pubIished over 150 refereed ar-
ticles in international journals, books,
and conferences and holds several U.S.
PatentS. He built his expertise through
research on a number of U.S. Depart-
ment of Energy and industry-funded
PrOjects. He is an IEEE Senior Member
and an IEEE Industrial Electronics So_
Ciety member.
KasAaSiIe @marasinghek the area of next-generation resilient
@vcu.edu) received his B.Sc, degree
in computer science from the Univer-
Sity of Peradeniya, Sri Lanka, in 2011.
He is currently pursuing his doctoral
degree in computer science at Virginia
Commonwealth University, Richmond.
His research interests include machine
learning, artificial neural networks,
fuzzy systems, deep learning, data
mining, and natura=anguage process-
ing. Furthermore, his interests extend
to applications of such algorithms to a
multitude of domains, including build-
1ng energy-management SyStemS. He
has gained experience on building
energy-management SyStemS from
multiple research projects funded by
the U.S" Department of Energy and in-
dustry leaders. He is an IEEE Student
Member and a member of the IEEE In_
dustrial Electronics Society.
Jn J: RigrIe2noa (jjrdguez
@uvigo.e;) received his M.Sc. degree
from the Ttchnical University of Ma-
drid, Spain, in 1990, and his Ph.D. de-
gree from the University ofVigo, Spain,
in 1996, both in electrical engineering.
He is an associate professor in the De-
Partment Of EIectronic TechnoIogy,
University of Vigo, In 2010-201l, he
WaS On Sabbatica=eave as a visiting
PrOfessor at the Advanced Diagnosis,
Automation, and ControI Laboratory,
Electrical and Computer Engineering
Department, North Carolina State Uni-
VerSity, Raleigh. His research interests
include the implementation of compIex
COntrOl and processing algorithms
in embedded pIatforms and concur-
rent testing of complex systems from
digital to industrial electronics. He has
authored over 140 journal and confer-
ence articles and holds several Span-
ish, European, aLnd U.S. patents. He is
an IEEE Senior Member and an IEEE In_
dustrial EIectronics Society member.
egt? (Craig.rieger@inl.go
received his B.S. and M.S. degrees in
Chemical engineering from Montana
State University in 1983 and 1985, re-
SPeCtively, and a Ph"D. in engineering
and applied science from Idaho State
University in 2008. He is the chief con-
troI systems research engineer at the
Idaho National Laboratory (IND, Pio-
neering multidisciplinary research in
COntrOI systems. He has 20 years of soft-
Ware and hardware design experience
for process controI system upgrades
and new installations and has been a
technica=ead for several INL nuclear
facilities and various controI system ar-
Chitectures. He is an IEEE Senior Mem_
ber and a member of the IEEE Industrial
Electronics Society.
ReereeS
U S EnergyInformationAdminlStratlOn. (2015,
Ap) Amual energy outlook 2015 U.S. Dept.
Energy, WashlngtOn, D.C., Reference case,
Table 5. [Onlinel. Available: http.www.eia
.gov/energyexplained/index.cfm?page=
electricity_uSe
2] US Energy Informationdministration.
(2010) Manufacturing energy consump-
tlOn SurVey U.S. Dept. Energy, WashlngtOn,
D.C. [Online]. Available: http:www eia.govI
COnS umPt lOn/manufactu r lng
[3] U.S. Energy Information Administration. Ouly
2013). !nternationaLl energy outIook 2013 U S.
Dept. Energy, Report DOE/EIA-0484. [Online.
Available http:www.eia.gov/todayinenergy/
detail.php?jd=12251
M. Manic (2014, Dec). Integrated and col-
laborative building energy management
SyStem.Smart Grld NelSIetler [Onlme].
Available http:smartgrid ieee.org/december-
2014/1 1 93-integrated-and-COllaborative-bulldlng-
energy-management-SyStem
[5] D. Bruckner,JHaase, P Palensky, and G. Zuck-
er`Latest trends in integrating building auto-
mation and smart grids:in Proc. 38th Amc/
bnfdusO/ec/romCS Soc(e/y, 2012,
pp. 6285-6290.
[6] F Kupzog, T. Sauter, and K. Poammer, IT-
enabled integration of renewables: A concept
for the smart power grid:EA,J Embed-
dedSysVOl. 201l, PP. 1-8, Jan. 2011.
[7] D. Alderton, Vionx Energy Corporation distrib-
uted energy storage system demonstration:in
Proc. DOE OEeI 5tomge Pkmm fieeRe!e
and (drMeeg, Portland, OR, Sept. 2015.
[8] Johnson ControIs. (2016, July). Distrlbuted
energystorage system: L1000 In-Bulldlng [On-
1ine]. Avable: http:www.johnsoncontroIs
COm/-/medla/jcl/des/files/Pdfs-SePt-2016/
11000seIIsheeL_uPdatedO716.pdf