Energy consumption forecasting for buildings plays a significant role in building energy management, conservation and fault diagnosis. Owing to the ease of use and adaptability of optimal solution seeking, data-driven techniques have proved to be accurate and efficient tools in recent years. This study provides a comprehensive review on the existing data-driven approaches for building energy forecasting, such as regression models, artificial neural networks, support vector machines, fuzzy models, grey models, etc. On this basis, the paper puts emphasis to the discussion on evolutionary algorithms hybridized models that combine evolutionary algorithms with regular data-driven models to improve prediction accuracy and robustness. Various combinations of such hybrid models are classified and their characteristics are analyzed. Finally, a detailed discussion on the advantages and challenges of current predictive models is provided.
Practical Application: Building energy consumption prediction is important for building energy management, efficiency and fault diagnosis. For existing buildings, multisourced, heterogeneous or inadequate data-driven models may lead to convergence problem or poor model accuracy. To this end, a state of art review on building energy forecasting technique is helpful for related professionals in the building industry.
U.S. Energy Information Administration. International energy outlook 2016, Washington, DC: U.S. Energy Information Administration, 2016.
2.
European Union. The directive 2010/31/EU of the European parliament and of the Council of 19 May 2010 on the energy performance of buildings. Brussels: European Commission, 2010.
3.
Tsinghua University Building Energy Center. China energy conservation annual development research report 2017 (in Chinese), Beijing: China Construction Industry Press, 2017.
4.
ZhaoHMagoulèsF. A review on the prediction of building energy consumption. Renew Sustain Energy Rev2012; 16: 3586–3592.
5.
FoucquierA, et al.State of the art in building modelling and energy performances prediction: a review. Renew Sustain Energy Rev2013; 23: 272–288.
6.
FumoN. A review on the basics of building energy estimation. Renew Sustain Energy Rev2014; 31: 53–60.
7.
AhmadAS, et al.A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renew Sustain Energy Rev2014; 33: 102–109.
8.
AmasyaliKEl-GoharyNM. A review of data-driven building energy consumption prediction studies. Renew Sustain Energy Rev2018; 81: 1192–1205.
9.
WangZSrinivasanRS. A review of artificial intelligence based building energy use prediction: contrasting the capabilities of single and ensemble prediction models. Renew Sustain Energy Rev2016; 75: 796–808.
10.
DebC, et al.A review on time series forecasting techniques for building energy consumption. Renew Sustain Energy Rev2017; 74: 902–924.
11.
AhmadT, et al.A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: a review. Energy Build2018; 165: 301–320.
12.
YildizBBilbaoJISproulAB. A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renew Sustain Energy Rev2017; 73: 1104–1122.
13.
Mat DautMA, et al.Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: a review. Renew Sustain Energy Rev2017; 70: 1108–1118.
14.
PanapakidisIPDagoumasAS. Day-ahead electricity price forecasting via the application of artificial neural network based models. Appl Energy2016; 172: 132–151.
15.
SudheerGSuseelathaA. Short term load forecasting using wavelet transform combined with Holt-Winters and weighted nearest neighbor models. Int J Electr Power Energy Syst2015; 64: 340–346.
16.
KaytezF, et al.Forecasting electricity consumption: a comparison of regression analysis, neural networks and least squares support vector machines. Int J Electr Power Energy Syst2015; 67: 431–438.
17.
PereiraCMAlmeidaNNDVellosoMLF. Fuzzy modeling to forecast an electric load time series. Proc Comput Sci2015; 55: 395–404.
18.
JinM, et al.Short-term power load forecasting using grey correlation contest modeling. Exp Syst Appl2012; 39: 773–779.
19.
LeeWHongJ. A hybrid dynamic and fuzzy time series model for mid-term power load forecasting. Int J Electr Power Energy Syst2015; 64: 1057–1062.
20.
ViroteJNeves-SilvaR. Stochastic models for building energy prediction based on occupant behavior assessment. Energy Build2012; 53: 183–193.
21.
NajiS, et al.Estimating building energy consumption using extreme learning machine method. Energy2016; 97: 506–516.
22.
ZhuangJ, et al.Building cooling load prediction based on time series method and neural networks. Int J Grid Distribut Comput2015; 8: 1386–1390.
23.
TurhanC, et al.Comparative study of a building energy performance software (KEP-IYTE-ESS) and ANN-based building heat load estimation. Energy Build2014; 85: 115–125.
24.
Bektas EkiciBAksoyUT. Prediction of building energy needs in early stage of design by using ANFIS. Expert Syst Appl2011; 38: 5352–5358.
25.
SunYWangSXiaoF. Development and validation of a simplified online cooling load prediction strategy for a super high-rise building in Hong Kong. Energy Convers Manag2013; 68: 20–27.
26.
DebC, et al.Forecasting diurnal cooling energy load for institutional buildings using artificial neural networks. Energy Build2016; 121: 284–297.
27.
Rezaeian-ZadehM, et al.Hourly air temperature driven using multi-layer perceptron and radial basis function networks in arid and semi-arid regions. Theor Appl Climatol2012; 109: 519–528.
28.
FuY, et al.Using support vector machine to predict next day electricity load of public buildings with sub-metering devices. Proc Eng2015; 121: 1016–1022.
29.
JovanovićRŽSretenovićAAŽivkovićBD. Ensemble of various neural networks for prediction of heating energy consumption. Energy Build2015; 94: 189–199.
30.
EfendiRIsmailZDerisMM. A new linguistic out-sample approach of fuzzy time series for daily forecasting of Malaysian electricity load demand. Appl Soft Comput2015; 28: 422–430.
31.
Kavousi-FardASametHMarzbaniF. A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting. Expert Syst Appl2014; 41: 6047–6056.
32.
LiG, et al.A research on short term load forecasting problem applying improved grey dynamic model. Int J Electr Power Energy Syst2011; 33: 809–816.
33.
LüX, et al.Modeling and forecasting energy consumption for heterogeneous buildings using a physical-statistical approach. Appl Energy2015; 144: 261–275.
34.
LiP, et al.Application of a hybrid quantized Elman neural network in short-term load forecasting. Int J Electr Power Energy Syst2014; 55: 749–759.
35.
LiKSuHChuJ. Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: a comparative study. Energy Build2011; 43: 2893–2899.
36.
YunK, et al.Building hourly thermal load prediction using an indexed ARX model. Energy Build2012; 54: 225–233.
37.
FanG, et al.Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing2016; 173: 958–970.
38.
ChaeYT, et al.Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings. Energy Build2016; 111: 184–194.
39.
ZhangF, et al.Time series forecasting for building energy consumption using weighted support vector regression with differential evolution optimization technique. Energy Build2016; 126: 94–103.
40.
BrownMChrisBBrownZ. Kernel regression for real-time building energy analysis. J Build Perform Simul2012; 5: 263–276.
41.
JuFHongW. Application of seasonal SVR with chaotic gravitational search algorithm in electricity forecasting. Appl Math Model2013; 37: 9643–9651.
42.
RallapalliSRGhoshS. Forecasting monthly peak demand of electricity in India – a critique. Energy Policy2012; 45: 516–520.
43.
ChangPFanCLinJ. Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach. Int J Electr Power Energy Syst2011; 33: 17–27.
44.
AzadehASaberiMSerajO. An integrated fuzzy regression algorithm for energy consumption estimation with non-stationary data: a case study of Iran. Energy2010; 35: 2351–2366.
45.
HamzacebiCEsHA. Forecasting the annual electricity consumption of Turkey using an optimized grey model. Energy2014; 70: 165–171.
46.
KangJZhaoH. Application of improved grey model in long-term load forecasting of power engineering. Syst Eng Proc2012; 3: 85–91.
47.
AkdemirBçetinkayaN. Long-term load forecasting based on adaptive neural fuzzy inference system using real energy data. Energy Proc2012; 14: 794–799.
48.
PaiPHongW. Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms. Electr Power Syst Res2005; 74: 417–425.
49.
KataraSFaisalAEngmannGM. A time series analysis of electricity demand in Tamale, Ghana. Int J Stat Appl2014; 4: 269–275.
50.
EkonomouL. Greek long-term energy consumption prediction using artificial neural networks. Energy2010; 35: 512–517.
51.
BiancoV, et al.Analysis and forecasting of nonresidential electricity consumption in Romania. Appl Energy2010; 87: 3584–3590.
52.
KandananondK. Forecasting electricity demand in Thailand with an artificial neural network approach. Energies2011; 4: 1246–1257.
53.
BackADTrappenbergTP. Selecting inputs for modeling using normalized higher order statistics and independent component analysis. IEEE Tran Neural Networks2001; 12: 612–617.
54.
LiK, et al.Building’s electricity consumption prediction using optimized artificial neural networks and principal component analysis. Energy Build2015; 108: 106–113.
55.
KeloSDudulS. A wavelet Elman neural network for short-term electrical load prediction under the influence of temperature. Int J Electr Power Energy Syst2012; 43: 1063–1071.
56.
Roldán-BlayC, et al.Upgrade of an artificial neural network prediction method for electrical consumption forecasting using an hourly temperature curve model. Energy Build2013; 60: 38–46.
57.
BahramiSHooshmandRParastegariM. Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm. Energy2014; 72: 434–442.
58.
HooshmandRAmooshahiHParastegariM. A hybrid intelligent algorithm based short-term load forecasting approach. Int J Electr Power Energy Syst2013; 45: 313–324.
59.
CepericECepericVBaricA. A Strategy for short-term load forecasting by support vector regression machines. IEEE Trans Power System2013; 28: 4356–4364.
60.
MoazzamiMKhodabakhshianAHooshmandR. A new hybrid day-ahead peak load forecasting method for Iran’s National Grid. Appl Energy2013; 101: 489–501.
61.
XueJXuZWatadaJ. Building an integrated hybrid model for short-term and mid-term load forecasting with genetic optimization. Int J Innovat Comput Inform Control2012; 8: 7381–7391.
62.
LeungMC, et al.The use of occupancy space electrical power demand in building cooling load prediction. Energy Build2012; 55: 151–163.
63.
Escrivá-EscriváG, et al.New artificial neural network prediction method for electrical consumption forecasting based on building end-uses. Energy Build2011; 43: 3112–3119.
64.
BožićMStojanovićMStajićZ. Short-term electric load forecasting using least square support vector machines. Sunday Mirror2010; 28: 141–150.
65.
MassanaJ, et al.Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes. Energy Build2016; 130: 519–531.
66.
KwokSSKYuenRKKLeeEWM. An intelligent approach to assessing the effect of building occupancy on building cooling load prediction. Build Environ2011; 46: 1681–1690.
67.
PlatonRDehkordiVRMartelJ. Hourly prediction of a building’s electricity consumption using case-based reasoning, artificial neural networks and principal component analysis. Energy Build2015; 92: 10–18.
68.
ChenTWangY. Long-term load forecasting by a collaborative fuzzy-neural approach. Int J Electr Power Energy Syst2012; 43: 454–464.
69.
ChaturvediDKSinhaAPMalikOP. Short term load forecast using fuzzy logic and wavelet transform integrated generalized neural network. Int J Electr Power Energy Syst2015; 67: 230–237.
70.
KouhiSKeyniaF. A new cascade NN based method to short-term load forecast in deregulated electricity market. Energy Convers Manag2013; 71: 76–83.
71.
MengMNiuDSunW. Forecasting monthly electric energy consumption using feature extraction. Energies2011; 4: 1495–1507.
72.
KorolijaI, et al.Regression models for predicting UK office building energy consumption from heating and cooling demands. Energy Build2013; 59: 214–227.
73.
ZhangY, et al.Comparisons of inverse modeling approaches for predicting building energy performance. Build Environ2015; 86: 177–190.
74.
WuJ, et al.Short term load forecasting technique based on the seasonal exponential adjustment method and the regression model. Energy Convers Manag2013; 70: 1–9.
75.
WangY, et al.Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: a case study of China. Energy Policy2012; 48: 284–294.
76.
SchalkoffRJ. Artificial neural networks, New York: John Wiley & Sons, 1997.
77.
MenaR, et al.A prediction model based on neural networks for the energy consumption of a bioclimatic building. Energy Build2014; 82: 142–155.
78.
BreimanL. Random forests. Machine Learn2001; 45: 5–32.
79.
VapnikVGolowichSESmolaA. Support vector method for function approximation, regression estimation, and signal processing. Adv Neural Inform Process Syst1997; 9: 281–287.
80.
ZhuJHoiSCLyuMR. Robust regularized kernel regression. IEEE Trans Syst Man Cybernetics B2008; 38: 1639–1644.
81.
LutsJ, et al.A tutorial on support vector machine-based methods for classification problems in chemometrics. Anal Chim Acta2010; 665: 129–145.
82.
DongBCaoCLeeSE. Applying support vector machines to predict building energy consumption in tropical region. Energy Build2005; 37: 545–553.
83.
JainRK, et al.Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy. Appl Energy2014; 123: 168–178.
84.
ZadehLA. Fuzzy sets, information and control. Inform Control1965; 8: 338–353.
85.
BoltürkEÖztayşiBSariIU. Electricity consumption forecasting using fuzzy time series. IEEE Int Symp Comput Intell Inform2013; 48: 245–248.
86.
EnayatifarR, et al.Imperialist competitive algorithm combined with refined high-order weighted fuzzy time series (RHWFTS-CA) for short term load forecasting. Energy Convers Manag2013; 76: 1104–1116.
87.
SadaeiHJ, et al.Short-term load forecasting using a hybrid model with a refined exponentially weighted fuzzy time series and an improved harmony search. Int J Electr Power Energy Syst2014; 62: 118–129.
88.
DengJL. Control problems of grey system. Syst Control Lett1982; 1: 288–294.
89.
DengJL. Introduction to Grey system theory. J Grey Syst1989; 1: 1–24.
90.
PaoHFuHTsengC. Forecasting of CO2 emissions, energy consumption and economic growth in China using an improved grey model. Energy2012; 40: 400–409.
FanCXiaoFWangS. Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques. Appl Energy2014; 127: 1–10.
93.
WangZ, et al.A novel ensemble learning approach to support building energy use prediction. Energy Build2018; 159: 109–122.
94.
Leake DB. Case-based reasoning: experiences, lessons and future directions. Boston: MIT Press Cambridge, 1996.
95.
AamodtAPlazaE. Case-based reasoning: foundational issues, methodological variations, and system approaches. Ai Commun1994; 7: 39–59.
96.
MonfetD, et al.Development of an energy prediction tool for commercial buildings using case-based reasoning. Energy Build2014; 81: 152–160.
97.
Goldberg DE, et al. Genetic algorithm is search optimization and machine learning. 1989; xiii: 2104–2116.
98.
Defilippo SB, Neto GG and Hippert HS. Short-term load forecasting by artificial neural networks specified by genetic algorithms – a simulation study over a Brazilian dataset. Berlin: Springer-Verlag Berlin Heidelberg, 2015.
99.
HongW, et al.Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm. Int J Electr Power Energy Syst2013; 44: 604–614.
100.
JungHCKimJSHeoH. Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach. Energy Build2015; 90: 76–84.
101.
LiKSuH. Forecasting building energy consumption with hybrid genetic algorithm-hierarchical adaptive network-based fuzzy inference system. Energy Build2010; 42: 2070–2076.
102.
LeeYTongL. Forecasting energy consumption using a grey model improved by incorporating genetic programming. Energy Convers Manag2011; 52: 147–152.
103.
HsuCChenC. Applications of improved grey prediction model for power demand forecasting. Energy Convers Manag2003; 44: 2241–2249.
104.
Eberhart R and Kennedy J, A new optimizer using particle swarm theory. In: MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, 1995, pp. 39–43.
105.
ChenYYangYLiuCLiCLiL. A hybrid application algorithm based on the support vector machine and artificial intelligence: An example of electric load forecasting. Appl Math Model2015; 39: 2617–2632.
106.
AmjadyNDaraeepourA. Mid-term demand prediction of electrical power systems using a new hybrid forecast technique. IEEE Trans Power Syst2011; 26: 755–765.
107.
SonHKimC. Forecasting short-term electricity demand in residential sector based on support vector regression and fuzzy-rough feature selection with particle swarm optimization. Procedia Engineering2015; 118: 1162–1168.
108.
NiuDWangYWuDD. Power load forecasting using support vector machine and ant colony optimization. Expert Syst Appl2010; 37: 2531–2539.
109.
StornRPriceK. 704 Differential Evolution – a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim1997; 11: 341–359.
110.
KouhiSKeyniaFNajafi RavadaneghS. A new short-term load forecast method based on neuro-evolutionary algorithm and chaotic feature selection. Int J Electr Power Energy Syst2014; 62: 862–867.
111.
RaoRSavsaniVVakhariaD. Teaching-learning-based optimization: A novel method for constrained mechanical design optimization problems. Comput Aided Des2011; 43: 303–315.
112.
RaoRVPatelV. An improved teaching-learning-based optimization algorithm for solving unconstrained optimization problems. Sci Iran2013; 20: 710–720.
113.
LiKXieXXueWDaiXChenXYangX. A hybrid teaching-learning artificial neural network for building electrical energy consumption prediction. Energy Build2018; 174: 323–334.
