Elaris Computing Nexus
Privacy-Preserving MARL for P2P Energy Trading in Low-Voltage Communities
Elaris Computing Nexus
Received On : 26 May 2026
Revised On : 02 July 2026
Accepted On : 25 July 2026
Published On : 04 August 2026
Volume 02, 2026
Pages : 145-155
Abstract
In this paper, we present a privacy preserving MARL (multi-agent reinforcement learning) model for distributed P2P (peer-to-peer) energy exchange in a low voltage energy community with 55 prosumers. The model incorporates twin critic networks, multi-head attention, a counterfactual baseline, message passing and AC power-flow evaluation in a centralized-training, decentralized-execution setting. The results show that the proposed approach achieves the maximum increasing testing reward of -162.98 while maintaining the privacy of the prosumers and operational constraints of voltage and temperature. Through ablation analysis, we find that attentiveness, twin critics and counterfactual baseline improve Q-value estimation, convergence and policy stability. The framework also reduces dependence on utility, improves the decentralized trading efficiency, and does not incur an excessive computational burden, when compared to many benchmark MARL algorithms with real network constraints.
Keywords
Multi-Agent Reinforcement Learning, Peer-To-Peer Energy Trading, Energy Communities, Privacy Preservation, Energy Storage Systems, Low-Voltage Networks, AC Power Flow.
- E. A. Soto, L. B. Bosman, E. Wollega, and W. D. Leon-Salas, “Peer-to-peer energy trading: A review of the literature,” Applied Energy, vol. 283, p. 116268, Dec. 2020, doi: 10.1016/j.apenergy.2020.116268.
- J. Liu, H. Yang, and Y. Zhou, “Peer-to-peer energy trading of net-zero energy communities with renewable energy systems integrating hydrogen vehicle storage,” Applied Energy, vol. 298, p. 117206, Jun. 2021, doi: 10.1016/j.apenergy.2021.117206.
- A. Shrestha et al., “Peer-to-Peer energy trading in Micro/Mini-Grids for Local Energy Communities: A Review and case Study of NePAl,” IEEE Access, vol. 7, pp. 131911–131928, Jan. 2019, doi: 10.1109/access.2019.2940751.
- L. Ali et al., “Application of a Community Battery-Integrated microgrid in a Blockchain-Based local energy market accommodating P2P trading,” IEEE Access, vol. 11, pp. 29635–29649, Jan. 2023, doi: 10.1109/access.2023.3260253.
- C. Zhu, M. Dastani, and S. Wang, “A survey of multi-agent deep reinforcement learning with communication,” Autonomous Agents and Multi-Agent Systems, vol. 38, no. 1, Jan. 2024, doi: 10.1007/s10458-023-09633-6.
- E. Wang et al., “A MADRL-Based credit allocation approach for interactive Multi-Agents,” International Journal of Information Technology & Decision Making, vol. 24, no. 07, pp. 2117–2137, Feb. 2025, doi: 10.1142/s0219622025500312.
- M. A. Hady, S. Hu, M. Pratama, Z. Cao, and R. Kowalczyk, “Multi-agent reinforcement learning for resources allocation optimization: a survey,” Artificial Intelligence Review, vol. 58, no. 11, Aug. 2025, doi: 10.1007/s10462-025-11340-5.
- K. Bao, T. Shi, and S. Wang, “Engineering Application Progress of Multi-Agent Deep Reinforcement Learning,” 2025 IEEE 19th International Conference on Control & Automation (ICCA), pp. 791–796, Jun. 2025, doi: 10.1109/icca65672.2025.11129859.
- D. Liu, F. Ren, J. Yan, G. Su, W. Gu, and S. Kato, “Scaling up Multi-Agent Reinforcement Learning: An extensive survey on scalability issues,” IEEE Access, vol. 12, pp. 94610–94631, Jan. 2024, doi: 10.1109/access.2024.3410318.
- D. Shi, J. Tong, Y. Liu, and W. Fan, “Knowledge reuse of Multi-Agent reinforcement learning in cooperative tasks,” Entropy, vol. 24, no. 4, p. 470, Mar. 2022, doi: 10.3390/e24040470.
- F. L. Da Silva, G. Warnell, A. H. R. Costa, and P. Stone, “Agents teaching agents: a survey on inter-agent transfer learning,” Autonomous Agents and Multi-Agent Systems, vol. 34, no. 1, Dec. 2019, doi: 10.1007/s10458-019-09430-0.
- K. Zhang, Z. Yang, and T. Başar, “Multi-Agent Reinforcement Learning: A selective overview of theories and algorithms,” in Studies in systems, decision and control, 2021, pp. 321–384. doi: 10.1007/978-3-030-60990-0_12.
- T. Ikeda and T. Shibuya, “Centralized Training with Decentralized Execution Reinforcement Learning for Cooperative Multi-agent Systems with Communication Delay,” 2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE), pp. 135–140, Sep. 2022, doi: 10.23919/sice56594.2022.9905866.
- T. Li et al., “Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 24, no. 2, pp. 1240–1279, Jan. 2022, doi: 10.1109/comst.2022.3160697.
- Y. Emami et al., “Human-In-The-Loop Machine Learning for safe and ethical autonomous Vehicles: principles, challenges, and opportunities,” arXiv (Cornell University), Aug. 2024, doi: 10.48550/arxiv.2408.12548.
- A. Kayal and S. Ravimaran, “Experimental Evaluation of Coordinated Decision Making Strategies Based on Multi-Agent Reinforcement Learning,” 2026 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), pp. 1–9, Jan. 2026, doi: 10.1109/icses66558.2026.11478990.
- V. Markova, V. Shopov, and M. Dimitrova, “Multi-Agent Reinforcement Learning for Pedagogical Interaction with Emotion-Informed Behaviour,” 2026 22nd International Conference on Information Technology Based Higher Education and Training (ITHET), pp. 1–9, May 2026, doi: 10.1109/ithet69978.2026.11585150.
- L. Cai, J. Chen, R. G. Downey, and M. R. Fellows, “On the parameterized complexity of short computation and factorization,” Archive for Mathematical Logic, vol. 36, no. 4–5, pp. 321–337, Aug. 1997, doi: 10.1007/s001530050069.
- C. Lou, Z. Jin, W. Tang, G. Geng, J. Yang, and L. Zhang, “LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading,” IEEE Transactions on Smart Grid, p. 1, Jan. 2026, doi: 10.1109/tsg.2026.3684885.
- T. Perger, L. Wachter, A. Fleischhacker, and H. Auer, “PV sharing in local communities: Peer-to-peer trading under consideration of the prosumers’ willingness-to-pay,” Sustainable Cities and Society, vol. 66, p. 102634, Dec. 2020, doi: 10.1016/j.scs.2020.102634.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
The authors thank the laboratory staff for their technical assistance and support during the experimental work.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit: https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this Article
Yong Cui, “Privacy-Preserving MARL for P2P Energy Trading in Low-Voltage Communities”, Elaris Computing Nexus, pp. 145-155, 2026, doi: 10.65148/ECN/2026012.
Copyright
© 2026 Yong Cui. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.