Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control

TL;DR

Grid-Agent is an innovative multi-agent system powered by Large Language Models that enhances power grid stability and security by detecting and remediating violations using semantic reasoning, numerical analysis, and adaptive scalability.

Contribution

This work introduces Grid-Agent, a novel LLM-powered multi-agent framework that combines semantic reasoning with numerical methods for power grid control and violation mitigation.

Findings

Demonstrated superior violation mitigation on IEEE and CIGRE benchmark networks.

Showed effective coordination of agents for grid stability and safety.

Validated scalability with adaptive multi-scale network representations.

Abstract

Modern power grids face unprecedented complexity from Distributed Energy Resources (DERs), Electric Vehicles (EVs), and extreme weather, while also being increasingly exposed to cyberattacks that can trigger grid violations. This paper introduces Grid-Agent, an autonomous AI-driven framework that leverages Large Language Models (LLMs) within a multi-agent system to detect and remediate violations. Grid-Agent integrates semantic reasoning with numerical precision through modular agents: a planning agent generates coordinated action sequences using power flow solvers, while a validation agent ensures stability and safety through sandboxed execution with rollback mechanisms. To enhance scalability, the framework employs an adaptive multi-scale network representation that dynamically adjusts encoding schemes based on system size and complexity. Violation resolution is achieved through optimizing switch configurations, battery deployment, and load curtailment. Our experiments on IEEE and CIGRE benchmark networks, including the IEEE 69-bus, CIGRE MV, IEEE 30-bus test systems, demonstrate superior mitigation performance, highlighting Grid-Agent's suitability for modern smart grids requiring rapid, adaptive response.