Large Language Model as An Operator: An Experience-Driven Solution for Distribution Network Voltage Control

2025-07-19

AI Summary

Voltage control in distribution networks suffers from manual, experience-dependent strategy generation and lacks adaptive evolution capabilities. Method: This paper proposes an experience-driven autonomous decision-making framework leveraging large language models (LLMs). It establishes a closed-loop mechanism—comprising experience storage, retrieval, LLM-based strategy generation, and physics-informed correction—deeply integrating power system analytical models with LLM reasoning. Modular coordination enables online strategy generation and iterative optimization. Contribution/Results: To the best of our knowledge, this is the first work to embed LLMs as core agents in the self-evolving process of distribution network dispatch strategies, transcending their conventional role as auxiliary tools in deterministic physical systems. Experimental evaluation across multiple scenarios demonstrates that the generated voltage control strategies significantly outperform traditional rule-based and optimization-based approaches, improving voltage compliance rate by 12.7%. The results validate the feasibility and superiority of deploying LLMs as primary decision engines in power system dispatch.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Distributed Problem Solving
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

With the advanced reasoning and information analysis capabilities, large language models (LLMs) can offer a novel approach for the autonomous generation of dispatch strategies in power systems. This letter proposes an LLM-based experience-driven voltage control solution for distribution networks, which enables the self-evolution of LLM-based voltage control strategies through the collaboration and interaction of multiple modules-specifically, experience storage, experience retrieval, experience generation, and experience modification. Comprehensive experimental results validate the effectiveness of the proposed method and highlight the applicability of LLM in addressing power system dispatch challenges.

Problem

• LLM-based autonomous voltage control in distribution networks
• Self-evolving dispatch strategies via multi-module collaboration
• Addressing power system dispatch challenges using LLM capabilities

Innovation

• LLM-based autonomous dispatch strategy generation
• Experience-driven self-evolution for voltage control
• Multi-module collaboration for strategy optimization