This paper introduces an LLM agent that automates power grid static analysis by converting natural language into MATPOWER scripts. The framework utilizes DeepSeek-OCR to build an enhanced vector database from MATPOWER manuals. To ensure reliability, it devises a three-tier error-correction system: a static pre-check, a dynamic feedback loop, and a semantic validator. Operating via the Model Context Protocol, the tool enables asynchronous execution and automatically debugging in MATLAB. Experimental results demonstrate that the system achieves a 82.38% accuracy regarding the code fidelity, effectively eliminating hallucinations even in complex analysis tasks.
Cite
@article{arxiv.2604.09995,
title = {Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction},
author = {Qinjuan Wang and Shan Yang and Yongli Zhu},
journal= {arXiv preprint arXiv:2604.09995},
year = {2026}
}
Comments
This paper has been accepted for presentation at the 9th International Conference on Energy, Electrical and Power Engineering (CEEPE 2026) in Nanjing, China, April 17-19, 2026