Distributed IoT Climate Management for Residential Buildings via Cooperative Multi-Zone Reinforcement Learning with Federated Thermal Modeling

Residential HVAC systems consuming up to 48% of household energy operate predominantly under single-point thermostat control, a configuration that cannot differentiate thermal demand across zones. This article presents a distributed IoT climate management framework in which per-zone smart controllers form a self-healing wireless mesh, jointly optimize heating and cooling via a two-tier reinforcement learning architecture, and share thermal models through a federated aggregation protocol that preserves occupant-data privacy. Under a multi-zone residential testbed spanning six independently actuated zones over 90-day seasonal trials, the framework achieves 31.4% reduction in HVAC energy consumption relative to a single-thermostat baseline, of which 17-20 percentage points are attributable to the RL policy rather than to the occupancy instrumentation, with thermal comfort violation rates of 3.2% across occupied hours. The article describes system mechanics, experimental protocol, results across three building archetypes, and the specific conditions under which the performance gains do and do not generalize.

Internet of Things, residential HVAC control, multi-zone climate management, deep reinforcement learning

Ahrarinouri, M., Rastegar, M., & Seifi, A. R. (2021). Multiagent reinforcement learning for energy management in residential buildings. IEEE Transactions on Industrial Informatics, 17(1), 659-666. https://doi.org/10.1109/TII.2020.3007167

Balali, Y., Chong, A., Busch, A., & O'Keefe, S. (2023). Energy modelling and control of building heating and cooling systems with data-driven and hybrid models: A review. Renewable and Sustainable Energy Reviews, 183, 113496. https://doi.org/10.1016/j.rser.2023.113496

Khalil, M., Esseghir, M., & Merghem-Boulahia, L. (2022). A federated learning approach for thermal comfort management. Advanced Engineering Informatics, 52, 101526. https://doi.org/10.1016/j.aei.2022.101526

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Aguera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273-1282.

Mocanu, E., Mocanu, D. C., Nguyen, P. H., Liotta, A., Webber, M. E., Gibescu, M., & Slootweg, J. G. (2019). On-line building energy optimization using deep reinforcement learning. IEEE Transactions on Smart Grid, 10(4), 3698-3708. https://doi.org/10.1109/TSG.2018.2834219

Noh, S.-H., & Moon, H. J. (2023). Anomaly detection based on LSTM learning in IoT-based dormitory for indoor environment control. Buildings, 13(11), 2886. https://doi.org/10.3390/buildings13112886

Oldewurtel, F., Parisio, A., Jones, C. N., Gyalistras, D., Gwerder, M., Stauch, V., Lehmann, B., & Morari, M. (2012). Use of model predictive control and weather forecasts for energy efficient building climate control. Energy and Buildings, 45, 15-27. https://doi.org/10.1016/j.enbuild.2011.09.022

Vazquez-Canteli, J. R., & Nagy, Z. (2019). Reinforcement learning for demand response: A review of algorithms and modeling techniques. Applied Energy, 235, 1072-1089. https://doi.org/10.1016/j.apenergy.2018.11.002

Wang, Z., & Hong, T. (2020). Reinforcement learning for building controls: The opportunities and challenges. Applied Energy, 269, 115036. https://doi.org/10.1016/j.apenergy.2020.115036

Wei, Y., Jang-Jaccard, J., Xu, W., Sabrina, F., Camtepe, S., & Boulic, M. (2023). LSTM-autoencoder-based anomaly detection for indoor air quality time-series data. IEEE Sensors Journal, 23(4), 3787-3800. https://doi.org/10.1109/JSEN.2023.3240313

Yu, L., Sun, Y., Xu, Z., Shen, C., Yue, D., Jiang, T., & Guan, X. (2021). Multi-agent deep reinforcement learning for HVAC control in commercial buildings. IEEE Transactions on Smart Grid, 12(1), 407-419. https://doi.org/10.1109/TSG.2020.2986634

Zhang, W., Wu, Y., & Calautit, J. K. (2022). A review on occupancy prediction through machine learning for enhancing energy efficiency, air quality and thermal comfort in the built environment. Renewable and Sustainable Energy Reviews, 167, 112704. https://doi.org/10.1016/j.rser.2022.112704

Zhang, Z., Chong, A., Pan, Y., Zhang, C., & Lam, K. P. (2019). Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning. Energy and Buildings, 199, 472-490. https://doi.org/10.1016/j.enbuild.2019.07.029

Zhu, H., & Hong, T. (2023). Privacy preserved and decentralized thermal comfort prediction model for smart buildings using federated learning. Building and Environment, 237, 110271. https://doi.org/10.1016/j.buildenv.2023.110271