Multi-agent Reinforcement Learning for Low-Carbon P2P Energy Trading among Self-Interested Microgrids

TL;DR

This paper introduces a multi-agent reinforcement learning framework enabling self-interested microgrids to optimize P2P energy trading, increasing renewable use and economic welfare while reducing emissions.

Contribution

It presents a novel multi-agent RL approach with a market mechanism for microgrid P2P trading, enhancing renewable integration and economic benefits.

Findings

Learned bidding policies improve renewable utilization.

Reduces reliance on high-carbon electricity.

Increases community economic welfare.

Abstract

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.