Transparent and Explainable Energy Modelling for Informed Decision-Making in Smart Homes
Sagheer Abbas, Muhammad Faisal, Muhammad Asif, Farhan Ullah, Muhammad Asghar Khan, Areej Fatima
Abstract. The concept of smart homes is increasing in its reliance on data-centric infrastructures and is gradually adopting data-driven paradigms. Machine-learning methods have proved to be very effective in predicting residential electricity demand, these algorithms are commonly considered as black-box solutions and therefore limit the confidence of the user, hindering their practical implementation. Therefore, the motivation for transparent energy forecast models has increased very fast. The demand for transparent energy prediction models is growing rapidly. During the simulations, the XGBoost and LightGBM algorithms are simulated, with SHAP (Shapley Additive Explanations) to identify the key factors influencing energy consumption. The simulation results show that time-based features, indoor temperature, and occupancy are vital in determining electricity use. With 90.10% accuracy, low training time, and clear insights, the proposed framework helps residents and energy managers make smarter, more confident decisions.
Keywords
Smart Homes, Residential Electricity Demand Forecasting, Explainable Artificial Intelligence (XAI), SHAP (Shapley Additive Explanations
Published online 4/25/2026, 11 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Sagheer Abbas, Muhammad Faisal, Muhammad Asif, Farhan Ullah, Muhammad Asghar Khan, Areej Fatima, Transparent and Explainable Energy Modelling for Informed Decision-Making in Smart Homes, Materials Research Proceedings, Vol. 64, pp 960-970, 2026
DOI: https://doi.org/10.21741/9781644904091-119
The article was published as article 119 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Salsbury, T. (2012). Model predictive control of building energy systems with balanced model reduction. American Control Conference (ACC). https://doi.org/10.1109/ACC.2012.6315516
[2] Amasyali, K., & El-Gohary, N. M. (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81, 1192–1205. https://doi.org/10.1016/j.rser.2017.04.095
[3] Hong, T., D’Oca, S., Turner, W. J. N., & Taylor-Lange, S. C. (2015). An ontology to represent energy-related occupant behavior in buildings. Part I: Introduction to the DNAs framework. Building and Environment, 92, 764–777. https://doi.org/10.1016/j.buildenv.2015.02.019
[4] Morcillo-Jimenez, R., Rivas, J. M., Ruiz, M. D., Martin-Bautista, M. J., & Fernandez-Basso, C. (2025). Privacy-preserving energy analytics in smart offices via container-based federated learning. Internet of Things, 25, 101782. https://doi.org/10.1016/j.iot.2025.101782
[5] Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), Article 12. https://doi.org/10.1145/3298981
[6] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS). https://doi.org/10.48550/arXiv.1705.07874
[7] Amasyali, K., & El-Gohary, N. M. (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81, 1192–1205. https://doi.org/10.1016/j.rser.2017.04.095
[8] Zhang, Z., Rath, S., Xu, J., & Xiao, T. (2024). Federated learning for smart grid: A survey on applications and potential vulnerabilities. arXiv preprint arXiv:2409.10764. https://arxiv.org/abs/2409.10764
[9] Morcillo-Jimenez, R., Rivas, J. M., Ruiz, M. D., Martin-Bautista, M. J., & Fernandez-Basso, C. (2025). Privacy-preserving energy analytics in smart offices via container-based federated learning. Internet of Things, 25, 101782. https://doi.org/10.1016/j.iot.2025.101782
[10] Tukiainen, M., Rautiainen, A., & Lehtonen, M. (2022). Explainable artificial intelligence for energy forecasting in smart buildings. Energy and Buildings, 257, 111811. https://doi.org/10.1016/j.enbuild.2021.11181
