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

TL;DR

This paper introduces an LLM-based autonomous approach for day-ahead voltage control in distribution networks, enabling self-evolving dispatch strategies through experience management modules.

Contribution

It presents a novel experience-driven LLM framework for power system dispatch, integrating experience storage, retrieval, generation, and modification modules.

Findings

Experimental results confirm the effectiveness of the LLM-based approach.

The method improves dispatch decision accuracy under incomplete information.

Demonstrates the applicability of LLMs in power system control tasks.

Abstract

With the advanced reasoning, contextual understanding, and information synthesis capabilities of large language models (LLMs), a novel paradigm emerges for the autonomous generation of dispatch strategies in modern power systems. In this paper, we propose an LLM-based experience-driven day-ahead Volt/Var schedule solution for distribution networks, which enables the self-evolution of LLM agent's strategies through the collaboration and interaction of multiple modules, specifically, experience storage, experience retrieval, experience generation, and experience modification. The experience storage module archives historical operational records and decisions, while the retrieval module selects relevant past cases according to current forecasting conditions. The LLM agent then leverages these retrieved experiences to generate new, context-aware decisions for current situation, which are subsequently refined by the modification module to realize self-evolution of the dispatch policy. Comprehensive experimental results validate the effectiveness of the proposed method and highlight the applicability of LLMs in power system dispatch problems facing incomplete information.