Uncertainties in renewable generation and demand dynamics challenge day-ahead scheduling. To enhance renewable penetration and maintain intra-day balance, we develop a multi-agent reinforcement learning framework for self-interested microgrids participating in peer-to-peer (P2P) electricity trading. Each microgrid independently bids both price and quantity while optimizing its own profit via storage arbitrage under time-varying main-grid prices. A market-clearing mechanism coordinating trades and promoting incentive compatibility is proposed. Simulation results show that the learned bidding policy improves renewable utilization and reduces reliance on high-carbon electricity, while increasing community-level economic welfare, delivering a win-win situation in emission reduction and local prosperity.
@article{arxiv.2604.08973,
title = {Multi-agent Reinforcement Learning for Low-Carbon P2P Energy Trading among Self-Interested Microgrids},
author = {Junhao Ren and Honglin Gao and Lan Zhao and Qiyu Kang and Gaoxi Xiao and Yajuan Sun},
journal= {arXiv preprint arXiv:2604.08973},
year = {2026}
}