Artificial Intelligence–Driven Smart Home Energy Management Systems: Deep Learning–Based Load Forecasting, Optimization Strategies, and Open Research Challenges
DOI:
https://doi.org/10.31185/wjes.Vol14.Iss2.931Keywords:
Artificial Intelligence, Energy Efficiency, HVAC SystemsAbstract
Traditional residential buildings are progressively evolving into smart, adaptive, and energy-efficient environments through the combination of Artificial Intelligence (AI) and smart home technologies. In light of this development, this review provides a complete overview of recent research on AI-driven energy management in household settings. A total of 45 peer-reviewed articles available between 2019 and 2025 are systematically analyzed and categorized according to the adopted AI methods, including Machine Learning (ML), Deep Learning (DL), and Deep Reinforcement Learning (DRL), as well as hybrid frameworks. The reviewed studies primarily address energy optimization at the HVAC, lighting, and appliance level, with an emphasis on control architectures, deployment strategies, and algorithmic design aspects. Reported finding indicate that Multi-Agent Deep Reinforcement Learning (MADRL). systems can achieve electricity cost reductions , while maintaining satisfactory thermal comfort conditions. However, the literature also reveals determined challenges, particularly in relative to data privacy concerns, computational complexity, scalability across various buildings, and real-time control viability. In this paper, the researchers present a hybrid intelligent architecture that combines Proximal Policy Optimization (PPO), Long Short-Term Memory (LSTM) networks, and Graph Neural Networks (GNN) for the heating, cooling, and lighting modules of smart homes to control the usage of electrical energy. In this review, several approaches in the AI domain are compared and contrasted in order to point out the respective strength, weakness, and future of each and every one of them in the context of occupant comfort, efficiency, and sustainability in Buildings. The outcomes of this study aim to support researchers, system designers, and decision-makers in advancing robust and scalable AI-enabled smart home energy solutions. `
References
[1] J. Runge and R. Zmeureanu, “A review of deep learning techniques for forecasting energy use in buildings,” Feb. 01, 2021, MDPI AG. doi: 10.3390/en14030608.
[2] A. Manjavacas, A. Campoy-Nieves, J. Jiménez-Raboso, M. Molina-Solana, and J. Gómez-Romero, “An experimental evaluation of deep reinforcement learning algorithms for HVAC control,” Artif Intell Rev, vol. 57, no. 7, Jul. 2024, doi: 10.1007/s10462-024-10819-x.
[3] S. Ardabili, L. Abdolalizadeh, C. Mako, B. Torok, and A. Mosavi, “Systematic Review of Deep Learning and Machine Learning for Building Energy,” Mar. 18, 2022, Frontiers Media S.A. doi: 10.3389/fenrg.2022.786027.
[4] Y. A. Khan et al., “Enhancing Smart Home Efficiency with Heuristic-Based Energy Optimization,” Computers, vol. 14, no. 4, Apr. 2025, doi: 10.3390/computers14040149.
[5] X. Liu and Z. Gou, “Occupant-centric HVAC and window control: A reinforcement learning model for enhancing indoor thermal comfort and energy efficiency,” Build Environ, vol. 250, Feb. 2024, doi: 10.1016/j.buildenv.2024.111197.
[6] D. Zhuang, V. J. L. Gan, Z. Duygu Tekler, A. Chong, S. Tian, and X. Shi, “Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning,” Appl Energy, vol. 338, May 2023, doi: 10.1016/j.apenergy.2023.120936.
[7] J. Liu and J. Liu, “Research on Predicting Wind Turbine Power Generation based on Hybrid LSTM-GNN Model,” International Core Journal of Engineering, vol. 10, p. 2024, doi: 10.6919/ICJE.202412_10(12).0008.
[8] A. Deihim, D. Apostolopoulou, and E. Alonso, “Link to published version: Initial Estimate of AC Optimal Power Flow with Graph Neural Networks.”
[9] “Smart Home Energy Management Systems: A Systematic Review of Architecture, Communication, and Algorithmic Trends,” Journal of System and Management Sciences, Jun. 2024, doi: 10.33168/jsms.2024.1108.
[10] L. Yu, S. Qin, M. Zhang, C. Shen, T. Jiang, and X. Guan, “A Review of Deep Reinforcement Learning for Smart Building Energy Management,” Sep. 2021, doi: 10.1109/JIOT.2021.3078462.
[11] N. Ratković, “Integrating Machine Learning Techniques for Enhanced Energy Management and Sustainability in Smart Homes,” International Journal of Computations, Information and Manufacturing (IJCIM ), vol. 4, no. 1, p. 2024, doi: 10.54489/ijcim.v4i1.396.
[12] Q. W. Khan, R. Ahmad, A. Rizwan, A. N. Khan, K. T. Lee, and D. H. Kim, “Optimizing energy efficiency and comfort in smart homes through predictive optimization: A case study with indoor environmental parameter consideration,” Energy Reports, vol. 11, pp. 5619–5637, Jun. 2024, doi: 10.1016/j.egyr.2024.05.038.
[13] X. Fang et al., “Cross temporal-spatial transferability investigation of deep reinforcement learning control strategy in the building HVAC system level,” 2022. [Online]. Available: https://www.elsevier.com/open-access/userlicense/1.0/
[14] M. Arun, G. Gopan, S. Vembu, D. U. Ozsahin, H. Ahmad, and M. F. Alotaibi, “Internet of things and deep learning-enhanced monitoring for energy efficiency in older buildings,” Case Studies in Thermal Engineering, vol. 61, Sep. 2024, doi: 10.1016/j.csite.2024.104867.
[15] Y. Xiang, Y. Chen, J. Xu, and Z. Chen, “Research on sustainability evaluation of green building engineering based on artificial intelligence and energy consumption,” Nov. 01, 2022, Elsevier Ltd. doi: 10.1016/j.egyr.2022.08.266.
[16] P. Lissa, C. Deane, M. Schukat, F. Seri, M. Keane, and E. Barrett, “Deep reinforcement learning for home energy management system control,” Energy and AI, vol. 3, Mar. 2021, doi: 10.1016/j.egyai.2020.100043.
[17] M. H. Mjhool, H. Th. S. A. R. AL Rikabi, and M. S. F. AL Rikabi, “Enhancement the Efficiency of Solar Cell by using Internet of Things Applications,” Wasit Journal of Engineering Sciences, vol. 10, no. 1, Jun. 2022, doi: 10.31185/ejuow.Vol10.Iss1.229.
[18] B. Akhmetzhanov, B. Akhmetzhanov, D. Yedilkhan, A. Medeshova, K. Rabie, and N. Zhakiyev, “Multi-Layer Integration of Heterogeneous Wireless Sensor Networks for Smart Home Optimization,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 666–671. doi: 10.1016/j.procs.2023.12.166.
[19] V. Dankan Gowda, R. Samal, P. Reddy, A. V. G. A. Marthanda, R. K. Billady, and P. V. Rajlakshmi, “A Novel Framework for AI-Driven, Cloud-Integrated Energy-Efficient IoT Solutions in Smart Homes,” in 8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 327–332. doi: 10.1109/ICECA63461.2024.10800957.
[20] G. Mokhtari, A. Anvari-Moghaddam, and Q. Zhang, “A New Layered Architecture for Future Big Data-Driven Smart Homes,” IEEE Access, vol. 7, pp. 19002–19012, 2019, doi: 10.1109/ACCESS.2019.2896403.
[21] A. Varol, N. H. Motlagh, M. Leino, S. Tarkoma, and J. Virkki, “Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey,” Dec. 2024, [Online]. Available: http://arxiv.org/abs/2412.14708
[22] B. Amangeldy et al., “AI-Powered Building Ecosystems: A Narrative Mapping Review on the Integration of Digital Twins and LLMs for Proactive Comfort, IEQ, and Energy Management,” Sep. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/s25175265.
[23] Feyisayo Ajayi, Osho Moses Ademola, Kafilat Funmilola Amuda, and Bolape Alade, “AI-driven decarbonization of buildings: Leveraging predictive analytics and automation for sustainable energy management,” World Journal of Advanced Research and Reviews, vol. 24, no. 1, pp. 061–079, Oct. 2024, doi: 10.30574/wjarr.2024.24.1.2997.
[24] M. Huotari, A. Malhi, and K. Främling, “Machine Learning Applications for Smart Building Energy Utilization: A Survey,” Archives of Computational Methods in Engineering, vol. 31, no. 5, pp. 2537–2556, Jul. 2024, doi: 10.1007/s11831-023-10054-7.
[25] S. Kim, Y. Kim, M. Shin, A. Song, Y. Kim, and H. Y. Kim, “Development of an HVAC system control method using weather forecasting data with deep reinforcement learning algorithms.” [Online]. Available: https://ssrn.com/abstract=4497003
[26] N. Thapa, “Nitesh Thapa AI-Driven Approaches for Optimizing the Energy Efficiency of Integrated Energy System.”
[27] S. Ahmed, A. Rahman, and M. Ashrafuzzaman, “A SYSTEMATIC REVIEW OF AI AND MACHINE LEARNING-DRIVEN IT SUPPORT SYSTEMS: ENHANCING EFFICIENCY AND AUTOMATION IN TECHNICAL SERVICE MANAGEMENT,” American Journal of Scholarly Research and Innovation, vol. 2, no. 02, pp. 75–101, Sep. 2023, doi: 10.63125/fd34sr03.
[28] B. N. Alhasnawi, H. K. Hashim, M. Zanker, and V. Bureš, “The rising, applications, challenges, and future prospects of energy in smart grids and smart cities systems,” Jul. 01, 2025, Elsevier Ltd. doi: 10.1016/j.ecmx.2025.101162.
[29] M. A. Khan et al., “Optimizing smart home energy management for sustainability using machine learning techniques,” Discover Sustainability, vol. 5, no. 1, Dec. 2024, doi: 10.1007/s43621-024-00681-w.
[30] S. M. Sharifhosseini et al., “Investigating Intelligent Forecasting and Optimization in Electrical Power Systems: A Comprehensive Review of Techniques and Applications,” Nov. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/en17215385.
[31] L. Yu, T. Jiang, S. Qin, M. Zhang, C. Shen, and X. Guan, “Deep Reinforcement Learning for Smart Building Energy Management: A Survey”, doi: 10.48550/arXiv.2008.05074.
[32] K. Kurte et al., “Evaluating the adaptability of reinforcement learning based HVAC control for residential houses,” Sustainability (Switzerland), vol. 12, no. 18, Sep. 2020, doi: 10.3390/su12187727.
[33] G. Gao, J. Li, and Y. Wen, “DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning.”
[34] M. Teng, Z. M. A. Al-Hamdawee, A. B. M. Ali, K. Jin, and M. Ahmadi, “Integrating digital twins and neural networks for real-time temperature management in smart homes: An innovative approach using ZigBee networks,” Energy Reports, vol. 13, pp. 6201–6218, Jun. 2025, doi: 10.1016/j.egyr.2025.05.055.
[35] X. Liu, Y. Wu, and H. Wu, “Enhancing HVAC Energy Management through Multi-Zone Occupant-Centric Approach: A Multi-Agent Deep Reinforcement Learning Solution,” 2023. [Online]. Available: https://www.elsevier.com/open-access/userlicense/1.0/
[36] S. A. Aghili, A. Haji Mohammad Rezaei, M. Tafazzoli, M. Khanzadi, and M. Rahbar, “Artificial Intelligence Approaches to Energy Management in HVAC Systems: A Systematic Review,” Apr. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/buildings15071008.
[37] Á. López-Cardona, G. Bernárdez, P. Barlet-Ros, and A. Cabellos-Aparicio, “Proximal Policy Optimization with Graph Neural Networks for Optimal Power Flow,” Apr. 2025, doi: 10.5220/0013462700003967.
[38] H. Wang, X. Chen, N. Vital, Edward. Duffy, and A. Razi, “Energy Optimization for HVAC Systems in Multi-VAV Open Offices: A Deep Reinforcement Learning Approach,” Nov. 2023, [Online]. Available: http://arxiv.org/abs/2306.13333
[39] C. C. Onweh, A. Al-Habaibeh, and E. Manu, “A Review of Energy Efficiency Strategies in Smart Buildings: Integrating Occupant Comfort, HVAC Optimisation, and Building Automation,” Research and Reviews in Sustainability, vol. 1, no. 1, pp. 48–60, Oct. 2025, doi: 10.5334/rss.9.
[40] J. Ogundiran, E. Asadi, and M. Gameiro da Silva, “A Systematic Review on the Use of AI for Energy Efficiency and Indoor Environmental Quality in Buildings,” May 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/su16093627.
[41] M. A. Adewoyin, O. Adediwin, and A. J. Audu, “Artificial Intelligence and Sustainable Energy Development: A Review of Applications, Challenges, and Future Directions,” International Journal of Multidisciplinary Research and Growth Evaluation., vol. 6, no. 2, pp. 196–203, 2025, doi: 10.54660/.ijmrge.2025.6.2.196-203.
[42] A. C. Ikegwu, O. J. Obianuju, I. S. Nwokoro, M. O. Kama, and D. U. Ebem, “Investigating the Impact of AI/ML for Monitoring and Optimizing Energy Usage in Smart Home,” Artificial Intelligence Evolution, pp. 30–43, Jan. 2025, doi: 10.37256/aie.6120256065.
[43] K. Ukoba, K. O. Olatunji, E. Adeoye, T. C. Jen, and D. M. Madyira, “Optimizing renewable energy systems through artificial intelligence: Review and future prospects,” Nov. 01, 2024, SAGE Publications Inc. doi: 10.1177/0958305X241256293.
[44] T. Rodrigues, J. Morgado, M. Barros, A. Oliveira De Sá, and J. Cecílio, “AI-driven IoT recommender system for enhancing energy efficient management in smart houses,” Expert Syst Appl, vol. 296, Jan. 2026, doi: 10.1016/j.eswa.2025.129108.
[45] Y. Lin, J. Tang, J. Guo, S. Wu, and Z. Li, “Advancing AI-Enabled Techniques in Energy System Modeling: A Review of Data-Driven, Mechanism-Driven, and Hybrid Modeling Approaches,” Feb. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/en18040845.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Roaa A. Mohammed, Faisal Theyab Abed, Jamal Saad A. Omer, Rania Ragab Hussein
This work is licensed under a Creative Commons Attribution 4.0 International License.
