X-GridAgent-OPF: An LLM-Powered Agentic AI System for Automating OPF Modeling and Solution

Xin Chen – TAMU

As power systems grow increasingly complex and data-intensive, there is a pressing need for AI tools that can streamline modeling and decision-making processes. This talk introduces a novel agentic AI system powered by Large Language Models (LLMs) designed to automate the formulation and solution of Optimal Power Flow (OPF) problems. The system leverages recent advances in natural language processing and multi-agent orchestration to interpret high-level user intents, retrieve and process relevant grid data, construct mathematical OPF models, select appropriate solvers, and validate results—all with minimal human intervention. This work exemplifies how LLM-powered agentic AI systems can augment human expertise and transform traditional workflows in electric grid planning and operation.