A HYBRID ADAPTIVE FRAMEWORK FOR SMART HOME ENERGY MANAGEMENT INTEGRATING DEEP REINFORCEMENT LEARNING AND METAHEURISTIC OPTIMIZATION
DOI:
https://doi.org/10.33003/fjs-2026-1003-4671Keywords:
Smart Home Energy (HEMS), Deep Reinforcement Learning (DRL), Metaheuristic Optimization, Deman-Side Management, Renewable Energy Integration, Appliance Scheduling, User ComfortAbstract
With the increasing integration of renewable energy sources (RES) and smart, demand-responsive appliances, modern Home Energy Management Systems (HEMS) require advanced, adaptive control strategies to enhance energy efficiency and reduce operational costs. Traditional, static optimization techniques often fail to handle the high uncertainty, stochastic nature of renewable generation, and dynamic user preferences. This study proposes a novel, comprehensive hybrid adaptive framework for smart home energy management that integrates Deep Reinforcement Learning (DRL) with metaheuristic optimization. The proposed framework aims to minimize electricity costs, reduce peak-to-average ratios (PAR), and maximize user comfort. Within this framework, Deep Reinforcement Learning (specifically algorithms like DQN or Multi-Objective DRL) is utilized to learn optimal control policies in real time, adapting to unpredictable fluctuations in energy demand and price signals. Simultaneously, Metaheuristic Optimization algorithms (e.g., Genetic Algorithm, Particle Swarm Optimization, or Bacterial Foraging) are employed to handle complex, constraints-driven scheduling tasks that require global optimization capabilities, enabling the effective management of household appliances, energy storage systems (ESS), and electric vehicles (EVs). The synergy between DRL and metaheuristic techniques bridges the gap between fast, adaptive, real-time control (DRL) and precise, long-term, optimal planning (Metaheuristics). Performance evaluation, conducted through simulations, indicates that the hybrid approach significantly outperforms traditional methods by reducing energy bills (often by 20–50%) and lowering peak demand, while successfully ensuring that user comfort preferences are maintained. The study highlights the effectiveness of this adaptive framework in promoting energy sustainability, reducing grid dependence, and facilitating intelligent energy management in future residential, smart city scenarios.
References
Adebiyi, A. A., & Habyarimana, M. (2025). Systematic Review of Optimization Methodologies for Smart Home Energy Management Systems. Energies, 18(19), 5262.
Abedinia, O., Amjady, N., & Zareipour, H. (2021). A new metaheuristic algorithm based on PSO for optimal energy management in smart microgrids. Applied Energy, 289, 116587.
Adebiyi, A. A., & Habyarimana, M. (2025). Optimization techniques for home energy management systems: A systematic literature review. Sustainability, 17(2), Article 5262. https://doi.org/10.3390/su170205262 (pp. 1–28)
Ahmad, T., Zhang, D., & Yan, C. (2022). A fuzzy logic-based control strategy for stable power sharing in distributed renewable energy systems. Energy Conversion and Management, 257, 115453.
Ahmed, A., Khalid, M., & Rehman, S. (2020). Deep learning-based models for solar irradiance and photovoltaic power forecasting: A comprehensive review. Renewable & Sustainable Energy Reviews, 124, 109792.
Ahmed, A., Khalid, M., & Rehman, S. (2022). Real-time CPS monitoring for smart homes: High-frequency measurement streams and anomaly detection. Energy Conversion and Management, 251, 115147.
Akhtar, S., Ahmad, A., Hussain, M., & Malik, S. (2023). Differential evolution-based multi-objective optimization for hybrid electrical–thermal residential energy systems. Energy Conversion and Management, 284, 116986.
Al Muala, Z., Bany Issa, M. A., Sansó-Rubert, D., & Bello Bugallo, P. M. (2023). Realistic home energy management system considering the life cycle of photovoltaic and energy storage systems. Sustainability, 15(14), Article 11205. https://doi.org/10.3390/su151411205 (pp. 1–23)
Alam, M., Rahman, S., & Chowdhury, A. (2022). Time-sensitive networking for real-time communication in distributed residential energy systems. IEEE Transactions on Industrial Informatics, 18(7), 4661–4672.
Aldahmashi, A., & Ma, T. (2024). Deep reinforcement learning–enabled IoT-edge home energy management for cost-aware residential operation. Energy and Buildings, 307, 112626.
Alghassab, M. (2024). Fuzzy logic control for uncertainty management in smart residential energy systems: A real-time implementation study. Sustainable Energy Technologies and Assessments, 63, 102845.
Alghassab, M. (2024). Fuzzy logic–based energy management system for residential buildings in Saudi Arabia: A comparative study. Energy Reports, 11, 1212–1224. https://doi.org/10.1016/j.egyr.2024.01.042
Al-Musaylh, M. S., Deo, R. C., Wen, X., & Adamowski, J. (2022). Short-term residential load forecasting using hybrid ensemble learning and multi-objective optimization techniques. Applied Energy, 305, 117811.
Areola, R. I., Adetunmbi, A. O., & Okimi, T. O. (2024). Intelligent energy management system: Harnessing fuzzy logic for charge control. Journal of Engineering Research and Reports, 26(4), 120–132. https://doi.org/10.9734/jerr/2024/v26i41119 journaljerr.com
Attia, M., Mahmoud, K., & Lehtonen, M. (2024). Deep learning and multi-objective optimization for PV power forecasting under uncertain environmental conditions. Solar Energy, 269, 113040.
Awad, R., & Hussein, M. (2023). Distributed communication protocols for cooperative residential energy management in cyber-physical neighborhoods. IEEE Transactions on Smart Grid, 14(2), 987–998.
Al Muala, Z. A., Bany Issa, M. A., Sansó-Rubert Pascual, D., & Bello Bugallo, P. M. (2023). Realistic home energy management system considering the life cycle of photovoltaic and energy storage systems. Sustainability, 15(14), 11205
Almihat, M. G. M., & Munda, J. L. (2025). The Role of Smart Grid Technologies in Urban and Sustainable Energy Planning. Energies, 18(7), 1618.
Badar, A. Q. H., & Anvari-Moghaddam, A. (2022). Smart home energy management system – a review. Advances in Building Energy Research, 16(1), 118–143. https://doi.org/10.1080/17512549.2020.1806925.
Badar, A. Q., & Anvari-Moghaddam, A. (2022). A review on home energy management systems with a focus on future directions. Energy Systems, Advance online publication. https://doi.org/10.1007/s12667-022-00525-8 (Note: No page range yet due to online-first status in 2022–2025 databases)
Baek, J., & Choi, D. (2024). Fault-tolerant real-time control for PV–battery residential systems using predictive diagnostics. Energy Reports, 10, 189–203.
Basciftci, F., Tascikaraoglu, A., & Karakas, A. (2023). Hybrid metaheuristic–reinforcement learning control for residential battery management under uncertainty. Applied Energy, 345, 121245.
Basciftci, Y., Tascikaraoglu, A., & Demir, N. (2023). Hybrid MPC–reinforcement learning control for residential energy management. Electric Power Systems Research, 221, 109365.
Bayasgalan, A., Park, Y. S., Koh, S. B., & Son, S.-Y. (2024). Comprehensive review of building energy management models: Grid-interactive efficient building perspective. Energies, 17(19), Article 4794. https://doi.org/10.3390/en17194794 (pp. 1–25). (Note: Reviews MATLAB/Simulink-based modeling for multi-source residential systems, controls, HIL, and deployment from 2020–2024.)
Bhattacharya, S., & Islam, M. (2025). Comparative evaluation of grey wolf, whale, and improved PSO algorithms for residential multi-objective energy scheduling. Energy Reports, 11, 556–574.
Cavus, M., Dissanayake, D., & Bell, M. (2025). Deep-Fuzzy Logic Control for Optimal Energy Management: A Predictive and Adaptive Framework for Grid-Connected Microgrids. Energies, 18(4), 995.
Chen, X., Wang, Y., & Li, J. (2023). Architecting cyber-physical systems for smart energy: Interoperability, sensing, and control. IEEE Access, 11, 64321–64336.
Chen, X., Wang, Y., & Liu, H. (2023). Hybrid DRL–evolutionary optimization architecture for distributed microgrid energy management. IEEE Transactions on Smart Grid, 14(3), 2401–2414.
Chen, Y., & Li, Z. (2024). PID-based coordinated control of residential HVAC, PV, and battery storage under variable solar and load conditions. Energy and Buildings, 307, 112599.
Christopoulos, P., Vargas, J., & Mancilla-David, F. (2024). Edge-deployed reinforcement learning for residential energy optimization using embedded controllers. IEEE Transactions on Smart Grid, 15(1), 233–245.
Christopoulos, S., Fokaides, P. A., & Tsikalakis, A. (2024). Embedded implementation of deep reinforcement learning controllers for smart home energy management. IEEE Access, 12, 15560–15575.
Coello Coello, C. A. (2020). Thirty years of evolutionary multi-objective optimization: A historical view of the field. IEEE Computational Intelligence Magazine, 15(1), 67–82.
Coraci, D., Karanfil, F., & Ardagna, C. (2024). Transfer learning for reinforcement learning-based building energy control: A heterogeneous adaptation framework. Applied Energy, 352, 121985.
Deanseekeaw, P., Somana, S., & Limmeechokchai, B. (2024). Appliance-level energy optimization using deep reinforcement learning in residential scheduling. Sustainable Energy Technologies and Assessments, 59, 103234.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Catherine Madunagu, Gregory M. Wajiga, Asabe Sandra Ahmadu
This work is licensed under a Creative Commons Attribution 4.0 International License.
