Author(s)

Lei Qiu

Affiliation(s)

Ningbo University of Technology, Ningbo 315048, Zhejiang, China.

Corresponding Author

Lei Qiu

ABSTRACT

Building energy consumption prediction has emerged as a critical component in the global effort to achieve energy efficiency and sustainability in the built environment. This systematic review comprehensively analyzes the application of deep learning approaches in building energy consumption prediction, synthesizing findings from recent research published between 2018 and 2024. Our methodology involved a systematic search across major scientific databases, including IEEE Xplore, Science Direct, and Web of Science, yielding 127 relevant studies that met our inclusion criteria. The review reveals significant advancements in prediction accuracy through various deep learning architectures, with particular success in hybrid models combining multiple neural network types. Key findings indicate that transformer-based models and attention mechanisms show superior performance for long-term predictions, while LSTM networks excel in capturing short-term consumption patterns. However, challenges persist in data quality, model interpretability, and real-world deployment. This review provides valuable insights for researchers and practitioners, highlighting promising research directions in transfer learning, explainable AI, and integration with building management systems.

KEYWORDS

Building management systems; Green building; Built environment; Deep learning

CITE THIS PAPER

Lei Qiu. Deep learning approaches for building energy consumption prediction. Frontiers in Environmental Research. 2024, 2(3): 11-17. DOI: https://doi.org/10.61784/fer3012.

REFERENCES

[1] Bilgen, S. Structure and environmental impact of global energy consumption. Renewable and Sustainable Energy Reviews, 2014, 38, 890-902.

[2] Chen, Y, Guo, M, Chen, Z, et al. Physical energy and data-driven models in building energy prediction: A review. Energy Reports, 2022, 8, 2656-2671.

[3] Ahmad, T, Madonski, R, Zhang, D, et al. Data-driven probabilistic machine learning in sustainable smart energy/smart energy systems: Key developments, challenges, and future research opportunities in the context of smart grid paradigm. Renewable and Sustainable Energy Reviews, 2022, 160, 112128.

[4] Putrama, I M, Martinek, P. Heterogeneous data integration: Challenges and opportunities. Data in Brief, 2024, 110853.

[5] Yan, D, O’Brien, W, Hong, T, et al. Occupant behavior modeling for building performance simulation: Current state and future challenges. Energy and buildings, 2015, 107, 264-278.

[6] Fan, C, Wang, J, Gang, W, et al. Assessment of deep recurrent neural network-based strategies for short-term building energy predictions. Applied energy, 2019, 236, 700-710.

[7] Huang, K, Wang, Y, Tao, M, et al. Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks?---A Neural Tangent Kernel Perspective. Advances in neural information processing systems, 2020, 33, 2698-2709.

[8] Yin, Q, Han, C, Li, A, et al. A Review of Research on Building Energy Consumption Prediction Models Based on Artificial Neural Networks. Sustainability, 2024, 16(17): 7805.

[9] Mienye, I D, Swart, T G, Obaido, G. Recurrent neural networks: A comprehensive review of architectures, variants, and applications. Information, 2024, 15(9): 517.

[10] Durand, D, Aguilar, J, R-Moreno, M D. An analysis of the energy consumption forecasting problem in smart buildings using LSTM. Sustainability, 2022, 14(20): 13358.

[11] Jain, A, Zamir, A R, Savarese, S, et al. Structural-rnn: Deep learning on spatio-temporal graphs. In Proceedings of the ieee conference on computer vision and pattern recognition, (CVPR), Las Vegas, NV, USA, 2016, 5308-5317. DOI: 10.1109/CVPR.2016.573.

[12] Peng, J, Kimmig, A, Wang, D, et al. Energy consumption forecasting based on spatio-temporal behavioral analysis for demand-side management. Applied Energy, 2024, 374, 124027.

[13] Lu, C, Li, S, Lu, Z. Building energy prediction using artificial neural networks: A literature survey. Energy and Buildings, 2022, 262, 111718.

[14] Wang, W, Hu, Y, Zou, T, et al. A new image classification approach via improved MobileNet models with local receptive field expansion in shallow layers. Computational Intelligence and Neuroscience, 2020, (1), 8817849.

[15] Tien, P W, Wei, S, Darkwa, J, et al. Machine learning and deep learning methods for enhancing building energy efficiency and indoor environmental quality–a review. Energy and AI, 2022, 10, 100198.

[16] Fusco, F, Eck, B, Gormally, R, et al. Knowledge-and data-driven services for energy systems using graph neural networks. In 2020 IEEE International conference on big data (Big Data), Atlanta, GA, USA, 2020, 1301-1308. DOI: 10.1109/BigData50022.2020.9377845.

[17] Khan, A, Sohail, A, Zahoora, U, et al. A survey of the recent architectures of deep convolutional neural networks. Artificial intelligence review, 2020, 53, 5455-5516.

[18] Aradi, S. Survey of deep reinforcement learning for motion planning of autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(2): 740-759.

[19] Zhang, L, Wen, J, Li, Y, et al. A review of machine learning in building load prediction. Applied Energy, 2021, 285, 116452.

[20] Moreno, M V, Dufour, L, Skarmeta, A F, et al. Big data: the key to energy efficiency in smart buildings. Soft Computing, 2016, 20, 1749-1762.

[21] Khalil, M, McGough, A S, Pourmirza, Z, et al. Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption—A systematic review. Engineering Applications of Artificial Intelligence, 2022, 115, 105287.

[22] Liu, H, Chen, C. Data processing strategies in wind energy forecasting models and applications: A comprehensive review. Applied Energy, 2019, 249, 392-408.

[23] Thakkar, A, Lohiya, R. Fusion of statistical importance for feature selection in Deep Neural Network-based Intrusion Detection System. Information Fusion, 2023, 90, 353-363.

[24] Najafabadi, M M, Villanustre, F, Khoshgoftaar, T M, et al. Deep learning applications and challenges in big data analytics. Journal of big data, 2015, 2, 1-21.

[25] Amasyali, K, El-Gohary, N M. A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 2018, 81, 1192-1205.

[26] Lahat, D, Adali, T, Jutten, C. Multimodal data fusion: an overview of methods, challenges, and prospects. Proceedings of the IEEE, 2015, 103(9): 1449-1477.

[27] Amasyali, K, El-Gohary, N M. A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 2018, 81, 1192-1205.

[28] Lund, J R, Guzman, J. Developing seasonal and long-term reservoir system operation plans using HEC-PRM. US Army Corps of Engineers, Hydrologic Engineering Center. 1996.

[29] Neu, D A, Lahann, J, Fettke, P. A systematic literature review on state-of-the-art deep learning methods for process prediction. Artificial Intelligence Review, 2022, 55(2): 801-827.

[30] Manic, M, Amarasinghe, K, Rodriguez-Andina, J J, et al. Intelligent buildings of the future: Cyberaware, deep learning powered, and human interacting. IEEE Industrial Electronics Magazine, 2016, 10(4): 32-49.

[31] Xin, Q, Alazab, M, Díaz, V G, et al. A deep learning architecture for power management in smart cities. Energy Reports, 2022, 8, 1568-1577.

[32] Washom, B, Meagher, K. Improved Modeling Tools Development for High Penetration Solar (No. DOE-UCSD-0004680-1). Univ. of California, San Diego, CA (United States). 2014. DOI: https://doi.org/10.2172/1165262.

[33] Ali, Y,  Aly, H H. Short term wind speed forecasting using artificial and wavelet neural networks with and without wavelet filtered data based on feature selections technique. Engineering Applications of Artificial Intelligence, 2024, 133, 108201.

[34] Chambers, J C, Mullick, S K, Smith, D D. How to choose the right forecasting technique. Cambridge, MA, USA: Harvard University, Graduate School of Business Administration. 1971.

[35] Shaikh, P H, Nor, N B M, Nallagownden, P, et al. A review on optimized control systems for building energy and comfort management of smart sustainable buildings. Renewable and Sustainable Energy Reviews, 2014, 34, 409-429.