Dynamic Weighted Multi-Agent Reinforcement Learning with Hybrid Reward Mechanism for Microgrid Energy Scheduling
Abstract
With growing energy demand and increasing environmental concerns, optimizing energy scheduling is crucial for microgrids, as efficient and flexible energy systems. This paper proposes an innovative multi-agent reinforcement learning algorithm to address microgrid energy scheduling. This algorithm incorporates a dynamic weight allocation mechanism, enabling agents to flexibly adjust decision weights based on real-time changes in energy supply and demand, improving the adaptability of scheduling strategies. Furthermore, a reward function based on historical data and real-time status is designed to guide agents in learning optimal energy scheduling strategies. To validate the algorithm's effectiveness, a microgrid energy scheduling simulation platform was constructed to simulate energy production, consumption, and storage in various scenarios. Experimental results show that, compared with traditional algorithms, the proposed algorithm can improve microgrid energy efficiency by an average of 15% and reduce operating costs by 12%. In scenarios with a high proportion of renewable energy, the algorithm effectively reduces energy waste and increases renewable energy consumption by 20%. Furthermore, stability analysis demonstrates that the algorithm maintains stable scheduling performance in the face of energy supply and demand uncertainties, showing strong robustness. This study provides a new solution for microgrid energy scheduling, helping to improve its overall performance and sustainability.
Full Text:
PDFReferences
Li, S., Cao, D., Hu, W., Huang, Q., Chen, Z., & Blaabjerg, F. (2023). Multi-energy management of interconnected multi-microgrid systems using multi-agent deep reinforcement learning. Journal of Modern Power Systems and Clean Energy, 11(5), 1606-1617. doi: 10.35833/MPCE.2022.000473.
Safiri, S., Nikoofard, A., Khosravy, M., & Senjyu, T. (2022). Multi-agent distributed reinforcement learning algorithm for free-model economic-environmental power and CHP dispatch problems. IEEE Transactions on Power Systems, 38(5), 4489-4500. doi: 10.1109/TPWRS.2022.3217905.
Wang, Y., Qiu, D., Teng, F., & Strbac, G. (2023). Towards microgrid resilience enhancement via mobile power sources and repair crews: A multi-agent reinforcement learning approach. IEEE transactions on power systems, 39(1), 1329-1345. doi: 10.1109/TPWRS.2023.3240479
Fan, Z., Zhang, W., & Liu, W. (2023). Multi-agent deep reinforcement learning-based distributed optimal generation control of DC microgrids. IEEE Transactions on Smart Grid, 14(5), 3337-3351. doi: 10.1109/TSG.2023.3237200.
Zhou, Y., Ma, Z., Wang, T., Zhang, J., Shi, X., & Zou, S. (2024). Joint energy and carbon trading for multi-microgrid system based on multi-agent deep reinforcement learning. IEEE Transactions on Power Systems, 39(6), 7376-7388. doi: 10.1109/TPWRS.2024.3380070.
Wu, Y., Zhao, T., Yan, H., Liu, M., & Liu, N. (2023). Hierarchical hybrid multi-agent deep reinforcement learning for peer-to-peer energy trading among multiple heterogeneous microgrids. IEEE Transactions on Smart Grid, 14(6), 4649-4665. doi: 10.1109/TSG.2023.3250321.
Qiu, D., Chen, T., Strbac, G., & Bu, S. (2022). Coordination for multienergy microgrids using multiagent reinforcement learning. IEEE Transactions on Industrial Informatics, 19(4), 5689-5700. doi: 10.1109/TII.2022.3168319
Munir, M. S., Abedin, S. F., Tran, N. H., Han, Z., Huh, E. N., & Hong, C. S. (2021). Risk-aware energy scheduling for edge computing with microgrid: A multi-agent deep reinforcement learning approach. IEEE Transactions on Network and Service Management, 18(3), 3476-3497. doi: 10.1109/TNSM.2021.3049381.
Zhou, H., Aral, A., Brandić, I., & Erol-Kantarci, M. (2021). Multiagent Bayesian deep reinforcement learning for microgrid energy management under communication failures. IEEE Internet of Things Journal, 9(14), 11685-11698. doi: 10.1109/JIOT.2021.3131719.
Li, J., Yang, S., & Yu, T. (2022). Data‐driven cooperative load frequency control method for microgrids using effective exploration‐distributed multi‐agent deep reinforcement learning. IET renewable power generation, 16(4), 655-670. https://doi.org/10.1049/rpg2.12323
Krishankumar, R., Mishra, A. R., Rani, P., Ecer, F., Zavadskas, E. K., Ravichandran, K. S., & Gandomi, A. H. (2025). Two-Stage EDAS Decision Approach with Probabilistic Hesitant Fuzzy Information. Informatica, 36(1), 65-97. doi:10.15388/24-INFOR577
Fan, H., Lu, E., Yu, W., Du, L., Wang, H., & Wang, D. (2023). Multi-agent deep reinforcement learning for co-dispatch of energy and hydrogen storage in low-carbon building clusters. IEEE Transactions on Network Science and Engineering, 11(6), 5449-5462. doi: 10.1109/TNSE.2023.3243202
Wang, Y., Xiao, M., You, Y., & Poor, H. V. (2023). Optimized energy dispatch for microgrids with distributed reinforcement learning. IEEE Transactions on Smart Grid, 15(3), 2946-2956. doi: 10.1109/TSG.2023.3331467.
Li, J., & Zhou, T. (2023). Evolutionary multi-agent deep meta reinforcement learning method for swarm intelligence energy management of isolated multi-area microgrid with internet of things. IEEE Internet of Things Journal, 10(14), 12923-12937. doi: 10.1109/JIOT.2023.3253693.
Du, Y., Wu, J., Li, S., Long, C., & Onori, S. (2019). Coordinated energy dispatch of autonomous microgrids with distributed MPC optimization. IEEE Transactions on Industrial Informatics, 15(9), 5289-5298. doi: 10.1109/TII.2019.2899885
Lei, L., Tan, Y., Dahlenburg, G., Xiang, W., & Zheng, K. (2020). Dynamic energy dispatch based on deep reinforcement learning in IoT-driven smart isolated microgrids. IEEE internet of things journal, 8(10), 7938-7953.doi: 10.1109/JIOT.2020.3042007
Alkan, N., & Kahraman, C. (2025). Continuous Pythagorean Fuzzy Set Extension with Multi-Attribute Decision Making Applications. Informatica, 36(2), 241-283. doi:10.15388/25-INFOR584
Saha, A., Rage, K., Senapati, T., Chatterjee, P., Zavadskas, E. K., & Sliogerienė, J. (2025). A Consensus-Based MULTIMOORA Framework under Probabilistic Hesitant Fuzzy Environment for Manufacturing Vendor Selection. Informatica, 1-24. doi:10.15388/24-INFOR581
Mahmoodi, M., Shamsi, P., & Fahimi, B. (2015). Economic dispatch of a hybrid microgrid with distributed energy storage. IEEE Transactions on Smart Grid, 6(6), 2607-2614.doi: 10.1109/TSG.2014.2384031
DOI: https://doi.org/10.31449/inf.v49i21.10566
This work is licensed under a Creative Commons Attribution 3.0 License.