Energy demand in buildings is increasing because of development of countries around the world. Forecasting the energy consumption in buildings has become crucial for improving energy efficiency and sustainable development, and thereby reducing energy costs and environmental impact. This investigation presents a comprehensive review of machine learning techniques for forecasting energy consumption time series using actual data. Real-time data were collected from a smart grid that was installed in an experimental building and used to evaluate the efficacy and effectiveness of statistical and machine learning techniques. Four well-known artificial intelligence techniques, Artificial Neural Networks, Support Vector Machine, Classification and Regression Tree, and Linear Regression, were used to analyze energy consumption in single and ensemble scenarios. An in-depth review and analysis of the ‘hybrid model’ that combines forecasting and optimization techniques is presented. The comprehensive comparison demonstrates that the hybrid model is more accurate than the single and ensemble models. Both the accuracy of prediction and the suitability for use of these models are considered to support users in planning energy management.

Energy demand in buildings is increasing because of development of countries around the world. Forecasting the energy consumption in buildings has become crucial for improving energy efficiency and sustainable development, and thereby reducing energy costs and environmental impact. This investigation presents a comprehensive review of machine learning techniques for forecasting energy consumption time series using actual data. Real-time data were collected from a smart grid that was installed in an experimental building and used to evaluate the efficacy and effectiveness of statistical and machine learning techniques. Four well-known artificial intelligence techniques, Artificial Neural Networks, Support Vector Machine, Classification and Regression Tree, and Linear Regression, were used to analyze energy consumption in single and ensemble scenarios. An in-depth review and analysis of the ‘hybrid model’ that combines forecasting and optimization techniques is presented. The comprehensive comparison demonstrates that the hybrid model is more accurate than the single and ensemble models. Both the accuracy of prediction and the suitability for use of these models are considered to support users in planning energy management.

1. IEA, World energy outlook 2011 executive summary. 2011: International Energy Agency.
2. Chou, J.-S. and N.-T. Ngo, Smart grid data analytics framework for increasing energy savings in residential buildings. Automation in Construction, 2016. 72: p. 247-257.
3. Zhao, H.-x. and F. Magoulès, A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 2012. 16(6): p. 3586-3592.
4. Lee, Y.M., et al., Applying science and mathematics to big data for smarter buildings. Annals of the New York Academy of Sciences, 2013. 1295(1): p. 18-25.
5. Reinisch, C., et al., ThinkHome Energy Efficiency in Future Smart Homes. EURASIP Journal on Embedded Systems, 2011. 2011(1): p. 104617.
6. Spees, K. and L. Lave, Impacts of Responsive Load in PJM - Load Shifting and Real Time Pricing. The Energy Journal, 2008. 29: p. 101-122.
7. Mahmood, A., N. Javaid, and S. Razzaq, A review of wireless communications for smart grid. Renewable and Sustainable Energy Reviews, 2015. 41: p. 248-260.
8. Colak, I., et al., Smart grid projects in Europe: Current status, maturity and future scenarios. Applied Energy, 2015. 152: p. 58-70.
9. Di Santo, K.G., et al., A review on smart grids and experiences in Brazil. Renewable and Sustainable Energy Reviews, 2015. 52: p. 1072-1082.
10. Soares, J., et al., A multi-objective model for the day-ahead energy resource scheduling of a smart grid with high penetration of sensitive loads. Applied Energy, 2016. 162: p. 1074-1088.
11. Yuan, J. and Z. Hu, Low carbon electricity development in China—An IRSP perspective based on Super Smart Grid. Renewable and Sustainable Energy Reviews, 2011. 15(6): p. 2707-2713.
12. Leiva, J., A. Palacios, and J.A. Aguado, Smart metering trends, implications and necessities: A policy review. Renewable and Sustainable Energy Reviews, 2016. 55: p. 227-233.
13. Raza, M.Q. and A. Khosravi, A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings. Renewable and Sustainable Energy Reviews, 2015. 50: p. 1352-1372.
14. Ellegård, K. and J. Palm, Visualizing energy consumption activities as a tool for making everyday life more sustainable. Applied Energy, 2011. 88(5): p. 1920-1926.
15. Macedo, M.N.Q., et al., Demand side management using artificial neural networks in a smart grid environment. Renewable and Sustainable Energy Reviews, 2015. 41: p. 128-133.
16. Wissner, M., The Smart Grid – A saucerful of secrets? Applied Energy, 2011. 88(7): p. 2509-2518.
17. Wu, Y.-n., J. Chen, and L.-r. Liu, Construction of China's smart grid information system analysis. Renewable and Sustainable Energy Reviews, 2011. 15(9): p. 4236-4241.
18. Zong, Y., et al., Challenges of implementing economic model predictive control strategy for buildings interacting with smart energy systems. Applied Thermal Engineering, 2017. 114: p. 1476-1486.
19. Deb, C., et al., A review on time series forecasting techniques for building energy consumption. Renewable and Sustainable Energy Reviews, 2017. 74: p. 902-924.
20. Chou, J.-S. and N.-T. Ngo, Time series analytics using sliding window metaheuristic optimization-based machine learning system for identifying building energy consumption patterns. Applied Energy, 2016. 177: p. 751-770.
21. Ahmad, A.S., et al., A review on applications of ANN and SVM for building electrical energy consumption forecasting. Renewable and Sustainable Energy Reviews, 2014. 33: p. 102-109.
22. Biswas, M.A.R., M.D. Robinson, and N. Fumo, Prediction of residential building energy consumption: A neural network approach. Energy, 2016. 117: p. 84-92.
23. Khandelwal, I., R. Adhikari, and G. Verma, Time Series Forecasting Using Hybrid ARIMA and ANN Models Based on DWT Decomposition. Procedia Computer Science, 2015. 48: p. 173-179.
24. Zhang, W., et al., Development forecast and technology roadmap analysis of renewable energy in buildings in China. Renewable and Sustainable Energy Reviews, 2015. 49: p. 395-402.
25. Lim, Y.-D., et al., A predictive demand of the maximum electric power using chaos-fuzzy, in The 10th IEEE International Conference. 2001, Fuzzy Systems. p. 1511-1514.
26. Lü, X., et al., Modeling and forecasting energy consumption for heterogeneous buildings using a physical–statistical approach. Applied Energy, 2015. 144: p. 261-275.
27. Monfet, Arkhipova, and Choiniere, Evaluation of a case-based reasoning energy prediction tool for commercial buildings, in Proceedings of the 13th international conference enhanc. build. oper. 2013: Montreal, Quebec, Canada. p. 1-7.
28. Mousavi, A. and V. Vyatkin, Energy Efficient Agent Function Block: A semantic agent approach to IEC 61499 function blocks in energy efficient building automation systems. Automation in Construction, 2015. 54: p. 127-142.
29. Kandananond, K., Forecasting Electricity Demand in Thailand with an Artificial Neural Network Approach. Energies, 2011. 4(12): p. 1246-1257.
30. Hu, Y., et al., A novel evolution tree for analyzing the global energy consumption structure. Energy, 2018. 147: p. 1177-1187.
31. Yip, S.-C., et al., Detection of energy theft and defective smart meters in smart grids using linear regression. International Journal of Electrical Power & Energy Systems, 2017. 91: p. 230-240.
32. Chujai, P., N. Kerdprasop, and K. Kerdprasop, Time Series Analysis of Household Electric Consumption with ARIMA and ARMA Models, in International MultiConference of Engineers and Computer Scientists. 2013, IMECS 2013: Hong Kong.
33. Khashei, M. and M. Bijari, A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Applied Soft Computing, 2011. 11(2): p. 2664-2675.
34. Tan, Z., et al., Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. Applied Energy, 2010. 87(11): p. 3606-3610.
35. Zhang, G.P., Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 2003. 50: p. 159-175.
36. Zhang, P., Time-series analysis with neural networks and ARIMA-neural network hybrids. Neurocomputing, 2001. 50: p. 159-175.
37. Chen, K.-Y. and C.-H. Wang, A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan. Expert Systems with Applications, 2007. 32(1): p. 254-264.
38. Pérez-Lombard, L., J. Ortiz, and C. Pout, A review on buildings energy consumption information. Energy and Buildings, 2008. 40(3): p. 394-398.
39. Aghemo, C., L. Blaso, and A. Pellegrino, Building automation and control systems: A case study to evaluate the energy and environmental performances of a lighting control system in offices. Automation in Construction, 2014. 43: p. 10-22.
40. Corry, E., et al., A performance assessment ontology for the environmental and energy management of buildings. Automation in Construction, 2015. 57: p. 249-259.
41. Zhou, S., et al., Real-time Energy Control Approach for Smart Home Energy Management System. Electric Power Components and Systems, 2014. 42(3-4): p. 315-326.
42. Lee, Y.-S. and L.-I. Tong, Forecasting energy consumption using a grey model improved by incorporating genetic programming. Energy Conversion and Management, 2011. 52(1): p. 147-152.
43. Monfet, D., et al., Development of an energy prediction tool for commercial buildings using case-based reasoning. Energy and Buildings, 2014. 81: p. 152-160.
44. Allouhi, A., et al., Energy consumption and efficiency in buildings: current status and future trends. Journal of Cleaner Production, 2015. 109: p. 118-130.
45. Faria, P. and Z. Vale, Demand response in electrical energy supply: An optimal real time pricing approach. Energy, 2011. 36(8): p. 5374-5384.
46. Guo, J.J., J.Y. Wu, and R.Z. Wang, A new approach to energy consumption prediction of domestic heat pump water heater based on grey system theory. Energy and Buildings, 2011. 43(6): p. 1273-1279.
47. Hsu, D., Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data. Applied Energy, 2015. 160: p. 153-163.
48. Radulovic, F., et al., Guidelines for Linked Data generation and publication: An example in building energy consumption. Automation in Construction, 2015. 57: p. 178-187.
49. Sandels, C., et al., Day-ahead predictions of electricity consumption in a Swedish office building from weather, occupancy, and temporal data. Energy and Buildings, 2015. 108: p. 279-290.
50. Yang, J., et al., Energy performance model development and occupancy number identification of institutional buildings. Energy and Buildings, 2016. 123: p. 192-204.
51. Mat Daut, M.A., et al., Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review. Renewable and Sustainable Energy Reviews, 2017. 70: p. 1108-1118.
52. Fumo, N. and M.A. Rafe Biswas, Regression analysis for prediction of residential energy consumption. Renewable and Sustainable Energy Reviews, 2015. 47: p. 332-343.
53. Costa, A., et al., Key factors methodology—A novel support to the decision making process of the building energy manager in defining optimal operation strategies. Energy and Buildings, 2012. 49: p. 158-163.
54. Brockwell, P.J. and R.A. Davis, Introduction Time Series and Forecasting. Springer Texts in Statistics. Vol. XIII. 1996, New York: Springer-Verlag New York.
55. De Boeck, L., et al., Improving the energy performance of residential buildings: A literature review. Renewable and Sustainable Energy Reviews, 2015. 52: p. 960-975.
56. Fan, C., F. Xiao, and S. Wang, Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques. Applied Energy, 2014. 127: p. 1-10.
57. Foucquier, A., et al., State of the art in building modelling and energy performances prediction: A review. Renewable and Sustainable Energy Reviews, 2013. 23: p. 272-288.
58. Fumo, N., A review on the basics of building energy estimation. Renewable and Sustainable Energy Reviews, 2014. 31: p. 53-60.
59. Li, K., et al., Building's electricity consumption prediction using optimized artificial neural networks and principal component analysis. Energy and Buildings, 2015. 108: p. 106-113.
60. Mena, R., et al., A prediction model based on neural networks for the energy consumption of a bioclimatic building. Energy and Buildings, 2014. 82: p. 142-155.
61. Azadeh, A., M. Saberi, and O. Seraj, An integrated fuzzy regression algorithm for energy consumption estimation with non-stationary data: A case study of Iran. Energy, 2010. 35(6): p. 2351-2366.
62. Azadeh, A., O. Seraja, and M. Saberib, A Total Fuzzy Regression Algorithm for Energy Consumption Estimation, in Proceedings of the 6th IEEE international conference ind informatics. 2008: Daejeon, Korea. p. 1562–8.
63. Naji, S., et al., Application of adaptive neuro-fuzzy methodology for estimating building energy consumption. Renewable and Sustainable Energy Reviews, 2016. 53: p. 1520-1528.
64. Arghira, N., et al., Prediction of appliances energy use in smart homes. Energy, 2012. 48(1): p. 128-134.
65. Ekici, B.B. and U.T. Aksoy, Prediction of building energy consumption by using artificial neural networks. Advances in Engineering Software, 2009. 40(5): p. 356-362.
66. Hamzacebi, C. and H.A. Es, Forecasting the annual electricity consumption of Turkey using an optimized grey model. Energy, 2014. 70: p. 165-171.
67. Jung, H.C., J.S. Kim, and H. Heo, Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach. Energy and Buildings, 2015. 90: p. 76-84.
68. Yang, C., et al., High throughput computing based distributed genetic algorithm for building energy consumption optimization. Energy and Buildings, 2014. 76: p. 92-101.
69. Chou, J.-S. and A.S. Telaga, Real-time detection of anomalous power consumption. Renewable and Sustainable Energy Reviews, 2014. 33: p. 400-411.
70. Pereira, C.M., N.N.d. Almeida, and M.L.F. Velloso, Fuzzy Modeling to Forecast an Electric Load Time Series. Procedia Computer Science, 2015. 55: p. 395-404.
71. D'Andrea, E., B. Lazzerini, and S.L.d. Rosario, Neural network-based forecasting of energy consumption due to electric lighting in office buildings, in Sustainable Internet and ICT for Sustainability (SustainIT) 2012, IEEE: Pisa, Italy.
72. Mehdi, et al., Hourly air temperature driven using multi-layer perceptron and radial basis function networks in arid and semi-arid regions. Theoretical and Applied Climatology, 2012. 109(3-4): p. 519-528.
73. Adya, M. and F. Collopy, How effective are neural networks at forecasting and prediction? A review and evaluation. Forecasting, 1998. 17: p. 481-495.
74. Hamzaçebi, C., Forecasting of Turkey's net electricity energy consumption on sectoral bases. Energy Policy, 2007. 35(3): p. 2009-2016.
75. Nasr, G.E., E.A. Badr, and M.R. Younes, Neural networks in forecasting electrical energy consumption: univariate and multivariate approaches. International Journal of Energy Research, 2002. 26(1): p. 67-78.
76. Dong, B., C. Cao, and S.E. Lee, Applying support vector machines to predict building energy consumption in tropical region. Energy and Buildings, 2005. 37(5): p. 545-553.
77. Božić, M., M. Stojanović, and Z. Stajić, Short-term electric load forecasting using Least Square Support Vector Machines. Automatic Control and Robotics, 2010. 9: p. 141-150.
78. Catalina, T., J. Virgone, and E. Blanco, Development and validation of regression models to predict monthly heating demand for residential buildings. Energy and Buildings, 2008. 40(10): p. 1825-1832.
79. Hygh, J.S., et al., Multivariate regression as an energy assessment tool in early building design. Building and Environment, 2012. 57: p. 165-175.
80. Wang, Z. and R.S. Srinivasan, A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models. Renewable and Sustainable Energy Reviews, 2017. 75: p. 796-808.
81. Newsham, G.R. and B.J. Birt, Building-level Occupancy Data to Improve ARIMA-based Electricity Use Forecasts. 2010, Zurich, Switzerland: BuildSys. 13-18
82. Mohamed, N., M. Ahmad, and Z. Ismail, Short term load forecasting using double seasonal Arima model. Applied Science, 2011. 15: p. 223-231.
83. Chou, J.-S., C.-C. Ho, and H.-S. Hoang, Determining quality of water in reservoir using machine learning. Ecological Informatics, 2018. 44: p. 57-75.
84. Martínez-Álvarez, F., et al., A Survey on Data Mining Techniques Applied to Electricity-Related Time Series Forecasting. Energies, 2015. 8(12): p. 13162-13193.
85. Chou, J.-S. and C. Lin, Predicting Disputes in Public-Private Partnership Projects: Classification and Ensemble Models. Journal of Computing in Civil Engineering, 2013. 27(1): p. 51-60.
86. Qiu, X., et al., Ensemble Deep Learning for Regression and Time Series Forecasting. 2014.
87. Allende, H. and C. Valle, Ensemble Methods for Time Series Forecasting. 2017. 349: p. 217-232.
88. Soares, E., et al., Ensemble of evolving data clouds and fuzzy models for weather time series prediction. Applied Soft Computing, 2018. 64: p. 445-453.
89. Sallehuddin, R., M. Shamsuddin, and A. Abraham, Forecasting time series data using hybrid grey relationnal artificial neural network and auto regressive integrated moving average model. Neural Network World, 2007. 17(6): p. 573-605.
90. Lee, Y.-S. and L.-I. Tong, Forecasting nonlinear time series of energy consumption using a hybrid dynamic model. Applied Energy, 2012. 94: p. 251-256.
91. Chen, J., et al., Energy demand forecasting of the greenhouses using nonlinear models based on model optimized prediction method. Neurocomputing, 2016. 174: p. 1087-1100.
92. Chou, J.-S., M.-Y. Cheng, and Y.-W. Wu, Improving classification accuracy of project dispute resolution using hybrid artificial intelligence and support vector machine models. Expert Systems with Applications, 2013. 40(6): p. 2263-2274.
93. Coakley, D., P. Raftery, and M. Keane, A review of methods to match building energy simulation models to measured data. Renewable and Sustainable Energy Reviews, 2014. 37: p. 123-141.
94. Sapankevych, N. and R. Sankar, Time Series Prediction Using Support Vector Machines: A Survey. IEEE Computational Intelligence Magazine, 2009. 4(2): p. 24-38.
95. Suganthi, L. and A.A. Samuel, Energy models for demand forecasting—A review. Renewable and Sustainable Energy Reviews, 2012. 16(2): p. 1223-1240.
96. Amasyali, K. and N.M. El-Gohary, A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 2018. 81: p. 1192-1205.
97. Vapnik, V.N., The nature of statistical learning theory. 1995, New York, United States: Springer-Verlag.
98. Chou, J.-S., K.-H. Yang, and J.-Y. Lin, Peak Shear Strength of Discrete Fiber-Reinforced Soils Computed by Machine Learning and Metaensemble Methods. Journal of Computing in Civil Engineering, 2016. 30(6): p. 04016036.
99. Breiman, L., et al., Classification and Regression Trees. 1984, New York, United States: Taylor & Francis. 368.
100. Wang, S., J. Feng, and G. Liu, Application of seasonal time series model in the precipitation forecast. Mathematical and Computer Modelling, 2013. 58(3-4): p. 677-683.
101. Lin, L., et al., Random forests-based extreme learning machine ensemble for multi-regime time series prediction. Expert Systems with Applications, 2017. 83: p. 164-176.
102. Kittler, J., et al., On Combining Classifiers, in IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998, IEEE. p. 226-239.
103. Bashir, Z.A. and M.E. El-Hawary, Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks. IEEE Transactions on Power Systems, 2009. 24(1): p. 20-27.
104. Pradeepkumar, D. and V. Ravi, Forecasting financial time series volatility using Particle Swarm Optimization trained Quantile Regression Neural Network. Applied Soft Computing, 2017. 58: p. 35-52.
105. Hansen, J.V. and R.D. Nelson, Time-series analysis with neural networks and ARIMA-neural network hybrids. Experimental & Theoretical Artificial Intelligence, 2003. 15(3): p. 315-330.
106. Suykens, J.A.K., et al., Least Squares Support Vector Machines. 2002, Singapore: World Scientific, Singapore.
107. Kennedy, J. and R. Eberhart, Particle Swarm Optimization, in IEEE. 1995: Perth, WA, Australia.