A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics
Source abstract
Abstract
Buildings are among the largest energy consumers in the world. As new technologies have been developed, great advances have been made in buildings, turning conventional buildings into smart buildings. These smart buildings have allowed for greater supervision and control of the energy resources within the buildings, taking steps to energy management strategies to achieve significant energy savings. The forecast of energy consumption in buildings has been a very important element in these energy strategies since it allows adjusting the operation of buildings so that energy can be used more efficiently. This paper presents a review of energy consumption forecasting in smart buildings for improving energy efficiency. Different forecasting methods are studied in nonresidential and residential buildings. Following this, the literature is analyzed in terms of forecasting objectives, input variables, forecasting methods and prediction horizon. In conclusion, the paper examines future challenges for building energy consumption forecasting.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Building Energy and Comfort Optimization · Energy Load and Power Forecasting · Energy Efficiency and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Área de Ingeniería, Instituto Tecnológico de Santo Domingo, Santo Domingo 342-9, Dominican Republic
Departamento Ingeniería Agrícola y Forestal, Universidad de Valladolid, 42005 Soria, Spain
Área de Ciencias Básicas, Instituto Tecnológico de Santo Domingo, Santo Domingo 342-9, Dominican Republic
Centre for Energy Studies and Environmental Technologies (CEETA), Carretera a Camajuaní Km 5 ½, Universidad Central “Marta Abreu” de las Villas, Villa Clara 50100, Cuba
Departamento de Ingeniería Eléctrica, Universidad de Valladolid, 47011 Valladolid, Spain
References (100+)
Show source-provided references
1. A methodology for energy multivariate time series forecasting in smart buildings based on feature selection10.1016/j.enbuild.2019.05.021 ↗
2. (2020, June 12). IEA Tracking Buildings 2020. Available online: https://www.iea.org/reports/tracking-buildings-2020.
3. A novel hybrid modelling structure fabricated by using Takagi-Sugeno fuzzy to forecast HVAC systems energy demand in real-time for Basra city10.1016/j.scs.2020.102091 ↗
4. A practical artificial intelligence-based approach for predictive control in commercial and institutional buildings10.1016/j.enbuild.2019.109563 ↗
5. Runge, J., and Zmeureanu, R. (2019). Forecasting Energy Use in Buildings Using Artificial Neural Networks: A Review. Energies, 12.10.3390/en12173254 ↗
6. Simmons, C.R., Arment, J.R., Powell, K.M., and Hedengren, J.D. (2019). Proactive Energy Optimization in Residential Buildings with Weather and Market Forecasts. Processes, 7.10.3390/pr7120929 ↗
7. Distributed demand-side management optimisation for multi-residential users with energy production and storage strategies
8. Building Energy Management Systems: The Age of Intelligent and Adaptive Buildings10.1109/MIE.2015.2513749 ↗
9. A review of strategies for building energy management system: Model predictive control, demand side management, optimization, and fault detect & diagnosis10.1016/j.jobe.2020.101692 ↗
10. Intelligent techniques for forecasting electricity consumption of buildings10.1016/j.energy.2018.05.155 ↗
11. Combination of short-term load forecasting models based on a stacking ensemble approach10.1016/j.enbuild.2020.109921 ↗
12. Nugraha, G., Musa, A., Cho, J., Park, K., and Choi, D. (2018). Lambda-Based Data Processing Architecture for Two-Level Load Forecasting in Residential Buildings. Energies, 11.10.3390/en11040772 ↗
13. Prediction of building electricity usage using Gaussian Process Regression10.1016/j.jobe.2019.101054 ↗
14. Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data10.1016/j.enbuild.2020.110156 ↗
15. Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future10.1016/j.rser.2019.04.021 ↗
16. Reinforcement learning for demand response: A review of algorithms and modeling techniques10.1016/j.apenergy.2018.11.002 ↗
17. Predictions of electricity consumption in a campus building using occupant rates and weather elements with sensitivity analysis: Artificial neural network vs. linear regression10.1016/j.scs.2020.102385 ↗
18. A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review10.1016/j.enbuild.2018.01.017 ↗
19. Fotopoulou, E., Zafeiropoulos, A., Terroso-Sáenz, F., Şimşek, U., González-Vidal, A., Tsiolis, G., Gouvas, P., Liapis, P., Fensel, A., and Skarmeta, A. (2017). Providing Personalized Energy Management and Awareness Services for Energy Efficiency in Smart Buildings. Sensors, 17.10.3390/s17092054 ↗
20. A hybrid neuro-fuzzy inference system-based algorithm for time series forecasting applied to energy consumption prediction10.1016/j.apenergy.2020.114977 ↗
21. A regression-based approach to estimating retrofit savings using the Building Performance Database10.1016/j.apenergy.2016.07.087 ↗
22. Comparative study of data driven methods in building electricity use prediction10.1016/j.enbuild.2019.04.029 ↗
23. A data-driven strategy to forecast next-day electricity usage and peak electricity demand of a building portfolio using cluster analysis, Cubist regression models and Particle Swarm Optimization10.1016/j.jclepro.2020.123115 ↗
24. Lee, J., Kim, J., and Ko, W. (2019). Day-Ahead Electric Load Forecasting for the Residential Building with a Small-Size Dataset Based on a Self-Organizing Map and a Stacking Ensemble Learning Method. Appl. Sci., 9.10.3390/app9061231 ↗
25. Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold10.1016/j.enbuild.2018.12.032 ↗
26. Input variable selection for thermal load predictive models of commercial buildings10.1016/j.enbuild.2016.12.016 ↗
27. Transfer learning with seasonal and trend adjustment for cross-building energy forecasting10.1016/j.enbuild.2018.01.034 ↗
28. A review on time series forecasting techniques for building energy consumption10.1016/j.rser.2017.02.085 ↗
29. System identification and data fusion for on-line adaptive energy forecasting in virtual and real commercial buildings10.1016/j.enbuild.2016.08.014 ↗
30. Energy planning and forecasting approaches for supporting physical improvement strategies in the building sector: A review10.1016/j.rser.2016.06.040 ↗
31. Building thermal load prediction through shallow machine learning and deep learning10.1016/j.apenergy.2020.114683 ↗
32. A review on the prediction of building energy consumption10.1016/j.rser.2012.02.049 ↗
33. A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models10.1016/j.rser.2016.10.079 ↗
34. State of the art in building modelling and energy performances prediction: A review10.1016/j.rser.2013.03.004 ↗
35. Modeling and forecasting building energy consumption: A review of data-driven techniques10.1016/j.scs.2019.101533 ↗
36. Modeling and forecasting energy consumption for heterogeneous buildings using a physical–statistical approach10.1016/j.apenergy.2014.12.019 ↗
37. Data-driven predictive models for residential building energy use based on the segregation of heating and cooling days10.1016/j.energy.2020.118045 ↗
38. A hybrid prediction model for residential electricity consumption using holt-winters and extreme learning machine10.1016/j.apenergy.2020.115383 ↗
39. The building performance gap: Are modellers literate?10.1177/0143624416684641 ↗
40. Ha, S., Tae, S., and Kim, R. (2019). Energy Demand Forecast Models for Commercil Buildings in South Korea. Energies, 12.10.3390/en12122313 ↗
41. Short-term office building elevator energy consumption forecast using SARIMA10.1080/19401493.2019.1698657 ↗
42. Forecasting long-term electricity demand for cooling of Singapore’s buildings incorporating an innovative air-conditioning technology10.1016/j.enbuild.2016.05.073 ↗
43. Commercial building cooling energy forecasting using proactive system identification: A whole building experiment study10.1080/23744731.2016.1188654 ↗
44. A two-step approach to forecasting city-wide building energy demand10.1016/j.enbuild.2017.11.063 ↗
45. Forecasting Airport Building Electricity Demand on the Basis of Flight Schedule Information for Demand Response Applications10.3141/2603-04 ↗
46. Modeling and forecasting energy consumption for residential buildings in Algeria using bottom-up approach10.1016/j.enbuild.2015.12.030 ↗
47. Lee, D. (2020). Low-cost and simple short-term load forecasting for energy management systems in small and middle-sized office buildings. Energy Explor. Exploit., 014459871990096.10.1177/0144598719900964 ↗
48. Modelling electric and heat load profiles of non-residential buildings for use in long-term aggregate load forecasts10.1016/j.jup.2019.03.004 ↗
49. Szul, T., and Kokoszka, S. (2020). Application of Rough Set Theory (RST) to Forecast Energy Consumption in Buildings Undergoing Thermal Modernization. Energies, 13.10.3390/en13061309 ↗
50. Review of building energy modeling for control and operation10.1016/j.rser.2014.05.056 ↗
51. Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method10.1260/1748-3018.6.1.59 ↗
52. Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique10.1016/j.enbuild.2016.05.028 ↗
53. A comparative analysis of artificial neural network architectures for building energy consumption forecasting10.1177/1550147719877616 ↗
54. Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques10.1016/j.apenergy.2018.12.042 ↗
55. Application of Artificial Neuron Networks as energy consumption forecasting tool in the building of Regulatory Authority of Energy, Athens, Greece10.1016/j.egypro.2018.11.251 ↗
56. Yang, J., Tan, K.K., Santamouris, M., and Lee, S.E. (2019). Building Energy Consumption Raw Data Forecasting Using Data Cleaning and Deep Recurrent Neural Networks. Buildings, 9.10.3390/buildings9090204 ↗
57. Amber, K.P., Aslam, M.W., Mahmood, A., Kousar, A., Younis, M.Y., Akbar, B., Chaudhary, G.Q., and Hussain, S.K. (2017). Energy Consumption Forecasting for University Sector Buildings. Energies, 10.10.3390/en10101579 ↗
58. Kiprijanovska, I., Stankoski, S., Ilievski, I., Jovanovski, S., Gams, M., and Gjoreski, H. (2020). HousEEC: Day-Ahead Household Electrical Energy Consumption Forecasting Using Deep Learning. Energies, 13.10.3390/en13102672 ↗
59. Building energy performance forecasting: A multiple linear regression approach10.1016/j.apenergy.2019.113500 ↗
60. Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings10.1016/j.enbuild.2015.11.045 ↗
61. Nichiforov, C., Stamatescu, G., Stamatescu, I., and Făgărăşan, I. (2019). Evaluation of Sequence-Learning Models for Large-Commercial-Building Load Forecasting. Information, 10.10.20944/preprints201904.0318.v1 ↗
62. Cerquitelli, T., Malnati, G., and Apiletti, D. (2019). Exploiting Scalable Machine-Learning Distributed Frameworks to Forecast Power Consumption of Buildings. Energies, 12.10.3390/en12152933 ↗
63. Machine Learning Algorithms for Short-Term Load Forecast in Residential Buildings Using Smart Meters, Sensors and Big Data Solutions10.1109/ACCESS.2019.2958383 ↗
64. Neural network model for short-term and very-short-term load forecasting in district buildings10.1016/j.enbuild.2019.109408 ↗
65. Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load10.1016/j.apenergy.2019.01.022 ↗
66. Zor, K., Çelik, Ö., Timur, O., and Teke, A. (2020). Short-Term Building Electrical Energy Consumption Forecasting by Employing Gene Expression Programming and GMDH Networks. Energies, 13.10.3390/en13051102 ↗
67. Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings10.1016/j.apenergy.2017.03.034 ↗
68. Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian Processes10.1016/j.apenergy.2017.12.104 ↗
69. Day-ahead probabilistic PV generation forecast for buildings energy management systems10.1016/j.solener.2018.06.100 ↗
70. Li, Z., Friedrich, D., and Harrison, G.P. (2020). Demand Forecasting for a Mixed-Use Building Using Agent-Schedule Information with a Data-Driven Model. Energies, 13.10.3390/en13040780 ↗
71. Deployment of data-mining short and medium-term horizon cooling load forecasting models for building energy optimization and management10.1016/j.ijrefrig.2018.10.017 ↗
72. Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks10.1016/j.enbuild.2015.12.050 ↗
73. Novel dynamic forecasting model for building cooling loads combining an artificial neural network and an ensemble approach10.1016/j.apenergy.2018.07.085 ↗
74. Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes10.1016/j.enbuild.2016.08.081 ↗
75. Forecasting the heating and cooling load of residential buildings by using a learning algorithm “gradient descent”, Morocco10.1016/j.csite.2018.03.006 ↗
76. Load forecast on intelligent buildings based on temporary occupancy monitoring10.1016/j.enbuild.2016.01.028 ↗
77. Culaba, A.B., Del Rosario, A.J.R., Ubando, A.T., and Chang, J.-S. (2020). Machine learning-based energy consumption clustering and forecasting for mixed-use buildings. Int. J. Energy Res., er.5523.10.1002/er.5523 ↗
78. Short term electricity load forecasting for institutional buildings10.1016/j.egyr.2019.08.086 ↗
79. Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches10.1016/j.enbuild.2018.01.066 ↗
80. A method to predict cooling load of large commercial buildings based on weather forecast and internal occupancy10.1007/s11708-016-0424-8 ↗
81. Xypolytou, E., Meisel, M., and Sauter, T. (2017, January 18–22). Short-term electricity consumption forecast with artificial neural networks—A case study of office buildings. Proceedings of the 2017 IEEE Manchester PowerTech, Manchester, UK.10.1109/PTC.2017.7980874 ↗
82. Data fusion in predicting internal heat gains for office buildings through a deep learning approach10.1016/j.apenergy.2019.02.066 ↗
83. Toolbox for development and validation of grey-box building models for forecasting and control10.1080/19401493.2015.1046933 ↗
84. Developing a whole building cooling energy forecasting model for on-line operation optimization using proactive system identification10.1016/j.apenergy.2015.12.002 ↗
85. A Hybrid Short-Term Building Electrical Load Forecasting Model Combining the Periodic Pattern, Fuzzy System, and Wavelet Transform10.1007/s40815-019-00783-y ↗
86. Forecasting the Short-Term Electricity Consumption of Building Using a Novel Ensemble Model10.1109/ACCESS.2019.2925740 ↗
87. Gordillo-Orquera, R., Lopez-Ramos, L., Muñoz-Romero, S., Iglesias-Casarrubios, P., Arcos-Avilés, D., Marques, A., and Rojo-Álvarez, J. (2018). Analyzing and Forecasting Electrical Load Consumption in Healthcare Buildings. Energies, 11.10.3390/en11030493 ↗
88. Electricity load forecasting by an improved forecast engine for building level consumers10.1016/j.energy.2017.07.150 ↗
89. Electricity load forecasting using clustering and ARIMA model for energy management in buildings10.1002/2475-8876.12135 ↗
90. Le, T., Vo, M.T., Kieu, T., Hwang, E., Rho, S., and Baik, S.W. (2020). Multiple Electric Energy Consumption Forecasting Using a Cluster-Based Strategy for Transfer Learning in Smart Building. Sensors, 20.10.3390/s20092668 ↗
91. Short-term building load forecast based on a data-mining feature selection and LSTM-RNN method10.1002/tee.23144 ↗
92. Khan, Z.A., Hussain, T., Ullah, A., Rho, S., Lee, M., and Baik, S.W. (2020). Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework. Sensors, 20.10.3390/s20051399 ↗
93. Forecasting performance comparison of two hybrid machine learning models for cooling load of a large-scale commercial building10.1016/j.jobe.2018.10.006 ↗
94. A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis10.1016/j.enbuild.2018.06.050 ↗
95. Nebot, À., and Mugica, F. (2020). Energy Performance Forecasting of Residential Buildings Using Fuzzy Approaches. Appl. Sci., 10.10.3390/app10020720 ↗
96. Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings10.1016/j.energy.2019.116552 ↗
97. A hybrid model for building energy consumption forecasting using long short term memory networks10.1016/j.apenergy.2019.114131 ↗
98. A Scalable Long-Horizon Forecasting of Building Electricity Consumption
99. Accurate forecasting of building energy consumption via a novel ensembled deep learning method considering the cyclic feature10.1016/j.energy.2020.117531 ↗
100. Study on deep reinforcement learning techniques for building energy consumption forecasting10.1016/j.enbuild.2019.109675 ↗