A Systematic Review of Building Energy Consumption Prediction: From Perspectives of Load Classification, Data-Driven Frameworks, and Future Directions
Source abstract
Abstract
The rapid development of machine learning and artificial intelligence technologies has promoted the widespread application of data-driven algorithms in the field of building energy consumption prediction. This study comprehensively explores diversified prediction strategies for different time scales, building types, and energy consumption forms, constructing a framework for artificial intelligence technologies in this field. With the prediction process as the core, it deeply analyzes the four key aspects of data acquisition, feature selection, model construction, and evaluation. The review covers three data acquisition methods, considers seven key factors affecting building loads, and introduces four efficient feature extraction techniques. Meanwhile, it conducts an in-depth analysis of mainstream prediction models, clarifying their unique advantages and applicable scenarios when dealing with complex energy consumption data. By systematically combing the existing research, this paper evaluates the advantages, disadvantages, and applicability of each method and provides insights into future development trends, offering clear research directions and guidance for researchers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Building Energy and Comfort Optimization · Energy Load and Power Forecasting · Noise Effects and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101, China
School of Thermal Engineering, Shandong Jianzhu University, Jinan 250101, China
School of Environmental Science and Engineering, Tianjin University, Tianjin 300072, China
Department of Built Environment, Oslo Metropolitan University, 0130 Oslo, Norway
Funding
National Key Research and Development Program of China · the Technological Innovation Project of Shandong Province · Research Initiation Fund for Doctor of Shandong Jianzhu University
References (100+)
Show source-provided references
1. A comprehensive review of energy-related data for U.S. commercial buildings10.1016/j.enbuild.2019.01.020 ↗
2. Impact of internet of things paradigm towards energy consumption prediction: A systematic literature review10.1016/j.scs.2021.103624 ↗
3. A sustainable data-driven energy consumption assessment model for building infrastructures in resource constraint environment
4. A novel ensemble learning approach to support building energy use prediction10.1016/j.enbuild.2017.10.085 ↗
5. Data-driven estimation of building energy consumption with multi-source heterogeneous data10.1016/j.apenergy.2020.114965 ↗
6. IEA EBC annex 53: Total energy use in buildings—Analysis and evaluation methods10.1016/j.enbuild.2017.07.038 ↗
7. 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 ↗
8. A review of data-driven building energy consumption prediction studies10.1016/j.rser.2017.04.095 ↗
9. A behavior-orientated prediction method for short-term energy consumption of air-conditioning systems in buildings blocks10.1016/j.energy.2022.125940 ↗
10. Towards developing a systematic knowledge trend for building energy consumption prediction10.1016/j.jobe.2020.101967 ↗
11. Development of a key-variable-based parallel HVAC energy predictive model10.1007/s12273-021-0885-0 ↗
12. Calibrating building simulation models using multi-source datasets and meta-learned Bayesian optimization10.1016/j.enbuild.2022.112278 ↗
13. Reconstituted data-driven air conditioning energy consumption prediction system employing occupant-orientated probability model as input and swarm intelligence optimization algorithms10.1016/j.energy.2023.129799 ↗
14. Sensor deployment configurations for building energy consumption prediction10.1016/j.enbuild.2024.113888 ↗
15. A novel deep-learning framework for short-term prediction of cooling load in public buildings10.1016/j.jclepro.2023.139796 ↗
16. Predicting energy consumption of mosque buildings during the operation stage using deep learning approach10.1016/j.enbuild.2023.113829 ↗
17. An evolutionary deep learning model based on EWKM, random forest algorithm, SSA and BiLSTM for building energy consumption prediction10.1016/j.energy.2023.129795 ↗
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. A review of data-driven approaches for prediction and classification of building energy consumption10.1016/j.rser.2017.09.108 ↗
20. A review of uncertainty analysis in building energy assessment10.1016/j.rser.2018.05.029 ↗
21. Assessment of deep recurrent neural network-based strategies for short-term building energy predictions10.1016/j.apenergy.2018.12.004 ↗
22. Modeling and forecasting building energy consumption: A review of data-driven techniques10.1016/j.scs.2019.101533 ↗
23. A review on renewable energy and electricity requirement forecasting models for smart grid and buildings10.1016/j.scs.2020.102052 ↗
24. Applications of reinforcement learning for building energy efficiency control: A review10.1016/j.jobe.2022.104165 ↗
25. Building energy prediction using artificial neural networks: A literature survey10.1016/j.enbuild.2021.111718 ↗
26. Physical energy and data-driven models in building energy prediction: A review10.1016/j.egyr.2022.01.162 ↗
27. Ardabili, S., Abdolalizadeh, L., Mako, C., Torok, B., and Mosavi, A. (2022). Systematic Review of Deep Learning and Machine Learning for Building Energy. Front. Energy Res., 10.10.3389/fenrg.2022.786027 ↗
28. A review and reflection on open datasets of city-level building energy use and their applications10.1016/j.enbuild.2023.112911 ↗
29. Gao, H., Wang, X., Wu, K., Zheng, Y., Wang, Q., Shi, W., and He, M. (2023). A Review of Building Carbon Emission Accounting and Prediction Models. Buildings, 13.10.3390/buildings13071617 ↗
30. Liu, H., Liang, J., Liu, Y., and Wu, H. (2023). A Review of Data-Driven Building Energy Prediction. Buildings, 13.10.3390/buildings13020532 ↗
31. Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms10.1016/j.energy.2023.128446 ↗
32. Olu-Ajayi, R., Alaka, H., Owolabi, H., Akanbi, L., and Ganiyu, S. (2023). Data-Driven Tools for Building Energy Consumption Prediction: A Review. Energies, 16.10.3390/en16062574 ↗
33. Interpretable machine learning for building energy management: A state-of-the-art review10.1016/j.adapen.2023.100123 ↗
34. Energy modelling and control of building heating and cooling systems with data-driven and hybrid models—A review10.1016/j.rser.2023.113496 ↗
35. A comprehensive review on deep learning approaches for short-term load forecasting10.1016/j.rser.2023.114031 ↗
36. Building energy consumption prediction and optimization using different neural network-assisted models; comparison of different networks and optimization algorithms10.1016/j.engappai.2023.107356 ↗
37. Exploring the comprehensive integration of artificial intelligence in optimizing HVAC system operations: A review and future outlook10.1016/j.rineng.2024.103765 ↗
38. Beltrán-Velamazán, C., Monzón-Chavarrías, M., and López-Mesa, B. (2025). Predicting Energy and Emissions in Residential Building Stocks: National UBEM with Energy Performance Certificates and Artificial Intelligence. Appl. Sci., 15.10.3390/app15020514 ↗
39. A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings10.1016/j.rser.2015.04.065 ↗
40. Accurate ultra-short-term load forecasting based on load characteristic decomposition and convolutional neural network with bidirectional long short-term memory model10.1016/j.segan.2023.101129 ↗
41. Deep learning for estimating building energy consumption10.1016/j.segan.2016.02.005 ↗
42. Self-updating machine learning system for building load forecasting—Method, implementation and case-study on COVID-19 impact10.1016/j.segan.2022.100873 ↗
43. Probabilistic load forecasting for the low voltage network: Forecast fusion and daily peaks10.1016/j.segan.2023.100998 ↗
44. Short-term power load forecasting based on AC-BiLSTM model10.1016/j.egyr.2024.01.026 ↗
45. Ultra-short term power load forecasting based on CEEMDAN-SE and LSTM neural network10.1016/j.enbuild.2022.112666 ↗
46. Deep belief network based electricity load forecasting: An analysis of Macedonian case10.1016/j.energy.2016.07.090 ↗
47. Modelling aggregate hourly electricity consumption based on bottom-up building stock10.1016/j.enbuild.2018.04.010 ↗
48. Etxegarai, G., Zapirain, I., Camblong, H., Ugartemendia, J., Hernandez, J., and Curea, O. (2022). Photovoltaic Energy Production Forecasting in a Short Term Horizon: Comparison between Analytical and Machine Learning Models. Appl. Sci., 12.10.3390/app122312171 ↗
49. The IMBPC HVAC system: A complete MBPC solution for existing HVAC systems10.1016/j.enbuild.2016.03.043 ↗
50. Comparative study of univariate and multivariate strategy for short-term forecasting of heat demand density: Exploring single and hybrid deep learning models10.1016/j.egyai.2024.100343 ↗
51. Data augmentation strategy for short-term heating load prediction model of residential building10.1016/j.energy.2021.121328 ↗
52. Attention-based interpretable neural network for building cooling load prediction10.1016/j.apenergy.2021.117238 ↗
53. Automated machine learning-based framework of heating and cooling load prediction for quick residential building design10.1016/j.energy.2023.127334 ↗
54. A knowledge embedded graph neural network-based cooling load prediction method using dynamic data association10.1016/j.enbuild.2022.112635 ↗
55. A deep bi-directional long-short term memory neural network-based methodology to enhance short-term electricity load forecasting for residential applications10.1016/j.cie.2022.108364 ↗
56. Consensus-based time-series clustering approach to short-term load forecasting for residential electricity demand10.1016/j.enbuild.2023.113550 ↗
57. Efficient Short-Term Electricity Load Forecasting for Effective Energy Management
58. A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for Short-Term Load Forecasting10.1016/j.energy.2020.118874 ↗
59. Research on short-term and ultra-short-term cooling load prediction models for office buildings10.1016/j.enbuild.2017.08.077 ↗
60. Data-driven short term load forecasting with deep neural networks: Unlocking insights for sustainable energy management10.1016/j.epsr.2024.110376 ↗
61. Shirzadi, N., Nizami, A., Khazen, M., and Nik-Bakht, M. (2021). Medium-Term Regional Electricity Load Forecasting through Machine Learning and Deep Learning. Designs, 5.10.3390/designs5020027 ↗
62. Regional midterm electricity demand forecasting based on economic, weather, holiday, and events factors10.1002/tee.23049 ↗
63. National-scale electricity peak load forecasting: Traditional, machine learning, or hybrid model?10.1016/j.energy.2021.122366 ↗
64. Artificial Intelligence based accurately load forecasting system to forecast short and medium-term load demands10.3934/mbe.2021022 ↗
65. Improved Medium Term Approach for Load Forecasting of Nigerian Electricity Network Using Artificial Neuro-Fuzzy Inference System: A Case Study of University of Nigeria, Nsukka10.1016/j.procs.2023.01.232 ↗
66. Incorporating air temperature into mid-term electricity load forecasting models using time-series regressions and neural networks10.1016/j.energy.2023.127831 ↗
67. Electricity load forecast considering search engine indices10.1016/j.epsr.2021.107398 ↗
68. Mid-term electricity demand forecasting using improved variational mode decomposition and extreme learning machine optimized by sparrow search algorithm10.1016/j.energy.2022.125328 ↗
69. Mystakidis, A., Koukaras, P., Tsalikidis, N., Ioannidis, D., and Tjortjis, C. (2024). Energy Forecasting: A Comprehensive Review of Techniques and Technologies. Energies, 17.10.3390/en17071662 ↗
70. An effective dimensionality reduction approach for short-term load forecasting10.1016/j.epsr.2022.108150 ↗
71. Deep learning based short term load forecasting with hybrid feature selection10.1016/j.epsr.2022.108065 ↗
72. Integrating long-term economic scenarios into peak load forecasting: An application to Spain10.1016/j.energy.2017.08.113 ↗
73. Gray wolf optimization-based wind power load mid-long term forecasting algorithm10.1016/j.compeleceng.2023.108769 ↗
74. A review on buildings energy information: Trends, end-uses, fuels and drivers10.1016/j.egyr.2021.11.280 ↗
75. Predicting hourly heating load in residential buildings using a hybrid SSA–CNN–SVM approach10.1016/j.csite.2024.104516 ↗
76. Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods
77. Research on long term power load grey combination forecasting based on fuzzy support vector machine10.1016/j.compeleceng.2024.109205 ↗
78. Temporal inception convolutional network based on multi-head attention for ultra-short-term load forecasting10.1049/gtd2.12394 ↗
79. Modelling electric and heat load profiles of non-residential buildings for use in long-term aggregate load forecasts10.1016/j.jup.2019.03.004 ↗
80. A dynamic anomaly detection method of building energy consumption based on data mining technology10.1016/j.energy.2022.125575 ↗
81. Integrated performance optimization of industrial buildings in relation to thermal comfort and energy consumption: A case study in hot summer and cold winter climate10.1016/j.csite.2023.102991 ↗
82. Predicting industrial building energy consumption with statistical and machine-learning models informed by physical system parameters10.1016/j.rser.2022.113045 ↗
83. Existing industrial buildings—A review on multidisciplinary research trends and retrofit solutions10.1016/j.jobe.2024.108615 ↗
84. Simulating long-term energy consumption prediction in campus buildings through enhanced data augmentation and metaheuristic-optimized artificial intelligence10.1016/j.enbuild.2024.114191 ↗
85. Multi objective planning for sustainable retrofit of educational buildings10.1016/j.jobe.2019.100759 ↗
86. Enhancing energy efficiency through hourly assessments of passive interventions in educational-office buildings: A case study in a Mediterranean climate10.1016/j.egyr.2023.12.016 ↗
87. Analyzing energy consumption patterns of an educational building through data mining10.1016/j.jobe.2021.103385 ↗
88. Short-term energy consumption prediction method for educational buildings based on model integration10.1016/j.energy.2023.128580 ↗
89. AI-big data analytics for building automation and management systems: A survey, actual challenges and future perspectives10.1007/s10462-022-10286-2 ↗
90. An artificial intelligence (AI)-driven method for forecasting cooling and heating loads in office buildings by integrating building thermal load characteristics10.1016/j.jobe.2023.107855 ↗
91. Effects of weather forecasting on indoor comfort and energy savings in office buildings10.1016/j.buildenv.2022.109280 ↗
92. 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 ↗
93. Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings10.1016/j.enbuild.2020.110350 ↗
94. A review and analysis of regression and machine learning models on commercial building electricity load forecasting10.1016/j.rser.2017.02.023 ↗
95. Model input selection for building heating load prediction: A case study for an office building in Tianjin10.1016/j.enbuild.2017.11.002 ↗
96. Forecasting performance comparison of two hybrid machine learning models for cooling load of a large-scale commercial building10.1016/j.jobe.2018.10.006 ↗
97. A hybrid CNN-GRU based probabilistic model for load forecasting from individual household to commercial building10.1016/j.egyr.2023.05.090 ↗
98. Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks10.1016/j.apenergy.2020.115410 ↗
99. A data-driven approach based on quantile regression forest to forecast cooling load for commercial buildings10.1016/j.scs.2021.103511 ↗
100. Evaluation of residential customer elasticity for incentive based demand response programs10.1016/j.epsr.2017.12.017 ↗