Problem
Research questions and friction points this paper is trying to address.
microgrids
peer-to-peer market
renewable energy utilization
carbon emission reduction
market coordination
Multi-agent Reinforcement Learning-based Joint Design of Low-Carbon P2P Market and Bidding Strategy in Microgrids
🤖 AI Summary
This study addresses the challenge of low renewable energy utilization efficiency in microgrid communities caused by the uncertainty of renewable generation and real-time market volatility. To tackle this issue, the authors propose an intra-day peer-to-peer (P2P) electricity trading framework that integrates self-interested behavior with community-wide decarbonization objectives. The framework models each microgrid’s decision-making process as a decentralized partially observable Markov decision process (DEC-POMDP), solved via multi-agent reinforcement learning, and incorporates a novel market-clearing mechanism to provide macro-level coordination. While preserving individual microgrids’ autonomy and economic incentives, the design employs tailored incentives to enhance local renewable energy consumption, substantially reducing reliance on external high-carbon power sources and achieving synergistic optimization between individual profits and collective carbon reduction goals.
📝 Abstract
The challenges of the uncertainties in renewable energy generation and the instability of the real-time market limit the effective utilization of clean energy in microgrid communities. Existing peer-to-peer (P2P) and microgrid coordination approaches typically rely on certain centralized optimization or restrictive coordination rules which are difficult to be implemented in real-life applications. To address the challenge, we propose an intraday P2P trading framework that allows self-interested microgrids to pursue their economic benefits, while allowing the market operator to maximize the social welfare, namely the low carbon emission objective, of the entire community. Specifically, the decision-making processes of the microgrids are formulated as a Decentralized Partially Observable Markov Decision Process (DEC-POMDP) and solved using a Multi-Agent Reinforcement Learning (MARL) framework. Such an approach grants each microgrid a high degree of decision-making autonomy, while a novel market clearing mechanism is introduced to provide macro-regulation, incentivizing microgrids to prioritize local renewable energy consumption and hence reduce carbon emissions. Simulation results demonstrate that the combination of the self-interested bidding strategy and the P2P market design helps significantly improve renewable energy utilization and reduce reliance on external electricity with high carbon-emissions. The framework achieves a balanced integration of local autonomy, self-interest pursuit, and improved community-level economic and environmental benefits.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-Agent Reinforcement Learning
DEC-POMDP
Peer-to-Peer Energy Market
Low-Carbon Microgrid
Decentralized Bidding Strategy
🔎 Similar Papers
No similar papers found.
