Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets

2025-08-25

AI Summary

Existing P2P electricity trading markets and RL-based approaches predominantly optimize for efficiency or individual agent utility, neglecting real-time fairness guarantees under uncertainty. To address this, we propose FairMarket-RL: a fairness-aware multi-agent reinforcement learning framework that innovatively employs a large language model (LLM) as a tunable fairness evaluator—generating context-sensitive fairness scores integrated into a piecewise reward function to dynamically balance fairness and efficiency in continuous double auctions. Operating under partial observability and discrete action spaces, the framework jointly optimizes bidding strategies via MARL, double-auction mechanisms, and LLM-based critique. Experiments demonstrate significant improvements in bidirectional fairness, local energy consumption rate, and user cost reduction, while ensuring grid operator feasibility and maintaining robustness across diverse uncertainty scenarios.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Fair Division
• Machine Learning: Efficient ML / Green AI

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Peer-to-peer (P2P) energy trading is becoming central to modern distribution systems as rooftop PV and home energy management systems become pervasive, yet most existing market and reinforcement learning designs emphasize efficiency or private profit and offer little real-time guidance to ensure equitable outcomes under uncertainty. To address this gap, a fairness-aware multiagent reinforcement learning framework, FairMarket-RL, is proposed in which a large language model (LLM) critic shapes bidding policies within a continuous double auction under partial observability and discrete price-quantity actions. After each trading slot, the LLM returns normalized fairness scores Fairness-to-Grid (FTG), Fairness-Between-Sellers (FBS), and Fairness-of-Pricing (FPP) that are integrated into the reward via ramped coefficients and tunable scaling, so that fairness guidance complements, rather than overwhelms, economic incentives. The environment models realistic residential load and PV profiles and enforce hard constraints on prices, physical feasibility, and policy-update stability. Across a progression of experiments from a small pilot to a larger simulated community and a mixed-asset real-world dataset, the framework shifts exchanges toward local P2P trades, lowers consumer costs relative to grid-only procurement, sustains strong fairness across participants, and preserves utility viability. Sensitivity analyses over solar availability and aggregate demand further indicate robust performance, suggesting a scalable, LLM-guided pathway to decentralized electricity markets that are economically efficient, socially equitable, and technically sound.

Problem

• Ensuring equitable outcomes in peer-to-peer electricity markets under uncertainty
• Shaping bidding policies for fairness in continuous double auction markets
• Balancing economic incentives with fairness guidance using LLM critics

Innovation

• LLM-guided multi-agent reinforcement learning
• Fairness shaping with normalized scoring
• Continuous double auction under partial observability