Human supervised AI helps power system research with physics and governance
Human-Supervised Artificial Intelligence Researchers in Electric Power Systems: Knowledge, Physics, Simulation, and Governance for Large Language Models
Artificial Intelligence
Summary
Figuring out how electric power systems work needs careful checking of data, models, and calculations. The authors explain that big AI language models can help researchers find information and create code but still need experts to check that the results make sense with real physics. They suggest a way to combine AI, simulations, and human oversight so conclusions are reliable and can be reviewed later. This approach also encourages keeping good records to trace and reproduce research steps.
What this means in practice
- •For power system engineers: Incorporate AI-assisted workflows that translate research queries into simulations while ensuring human oversight of modeling assumptions and safety boundaries.
- •For software developers for power simulations: Develop tools that integrate large language models with simulation and validation software to improve task coordination and research efficiency.
A position paper. It proposes an approach and reports no results.
Authors
Xiangrui Meng, Jingcheng Liu, Ke Wang, Miaopeng Yu, Zhengping Lin
Abstract
Conclusions in power-system research require a clear evidential basis. Researchers need to understand the data sources, modelling assumptions, and solution procedures to assess the conditions under which a conclusion holds. Large language models (LLMs) can help researchers extract information from documents and translate research requests into code and tool calls, but their outputs still require physical validation. Focusing on human-supervised artificial intelligence (AI) researchers, this review examines power-system LLM applications and related scientific workflows, together with physics-grounded power AI studies, to discuss the conditions for using LLMs in scientific research. In the proposed knowledge-physics-simulation-governance framework, LLMs translate information and coordinate tasks, simulators and validation tools test models, and experts retain authority over critical assumptions, safety boundaries, and final conclusions. Research processes should preserve materials for review so that claims can be traced to their sources, computations can be reproduced, and failed attempts and approvals can be examined. On this basis, a staged development roadmap and requirements for research reporting are proposed. Evaluation should focus on research artifacts and their validation to assess whether LLMs can improve the efficiency of power-system research within clearly defined permissions.