Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction

Qinjuan Wang; Shan Yang; Yongli Zhu

eess.SYApr 11, 2026

Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction

Authors: Qinjuan Wang, Shan Yang, Yongli Zhu

Organizations: Sun Yat-sen University, Guangzhou, China

Abstract

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.

Figures & tables

Fig. 2 : Model Context Protocol (MCP) Introduction

Panel of Figure 3 — Fig. 3 : Example of DeepSeek-OCR processing

Ablation Configuration	RAG Mode 3
Ablation Configuration	RAG+	Feedback	Planner	Validator
Full Model	✓	✓	✓	✓
Single Pass	✓		✓	✓
Simple Search	✓	✓		✓
Execution Only	✓	✓	✓

TABLE I : Ablation Experiment: System Component Configurations

Task Type	Task ID	Natural Language Request
Easy	Task 1	Load case14. Increase the active load at bus 2 by 15%. Run a DC power flow and display the results.
	Task 2	Load case57. Run a standard AC power flow and a DC power flow. Compare the resulting voltage magnitudes (Vm) and active power branch flows (Pf) between the two methods to evaluate the accuracy of the DC linearization.
	Task 3	Load case39. Compare the convergence performance of the standard Newton-Raphson algorithm and the Fast Decoupled (XB) algorithm. Set the maximum number of iterations to 10 for both and report whether each algorithm successfully converges.
Hard	Task 1	Load case39. Calculate the Total Transfer Capability (TTC) from Area 1 to Area 2. Write a MATLAB loop that iteratively increases Area 2 loads and Area 1 generation by 5% increments. In each step, run a DC OPF and check if any branch flow exceeds its RATE_A limit. Stop the iteration at the last feasible point before a violation and print the maximum successfully transferred power in MW.
	Task 2	Load case9. Add a new generator at Bus 4 (a load bus). You must change Bus 4 type to PV in mpc.bus, add the generator row to mpc.gen, and add a cost row to mpc.gencost. Ensure the BUS_TYPE and generator location are perfectly synchronized before running OPF.
	Task 3	Run AC OPF on case30. Implement a user-defined linear constraint Pg1 + Pg2 $\leq$ 30 MW using mpc.A, mpc.l, and mpc.u. Manually calculate the column indices for Pg1 and Pg2 based on the variable ordering without using helper functions.

TABLE II : Representative Task Benchmarks

Fig. 7 : Overall system accuracy (GCA) across different configurations.

Fig. 8 : CSGF performance grouped by task complexity.

Agentic Code Generation

Agentic code generation uses AI agents to plan, write, test, and revise executable programs with tools and feedback.

See all 125 papers

Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation
May 29, 2026Hui Wu, Xiaoyang Wang, Zhong FanAutomated Program Repair Code Generation
Department of Engineering, University of Exeter · Department of Computer Science, University of Exeter
LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
Jul 20, 2026Daniela Rojas, Abdulwahab Albassam, Aidan G. Leung +11LLM Agent Orchestration LLM Agent Evaluation
Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, 92093, USA · Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, T6G 1H9, Canada
RestoreBench: Can AI Agents Restore Power Flow Convergence?
Aug 31, 2026Riccardo Mansutti, Andrea Pomarico, Robert Jakob +3Multi-Agent LLM Systems LLM Agent Evaluation
1ETH Zürich · 2Politecnico di Milano · 3Harvard University

May 29, 2026J/K move · Enter open · S save

Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation

Hui Wu, Xiaoyang Wang, Zhong Fan

Department of Engineering, University of Exeter · Department of Computer Science, University of Exeter

Automated Program Repair Code Generation Code Generation Benchmarks LLM Code Generation Language Model Probing

Open paper AskPDF arXiv

Large language models (LLMs) can turn grid-analysis requests into executable programs for power-system simulation, but utilities and research laboratories often require on-premise deployment. In this setting, first-pass failures frequently arise at an API-knowledge boundary, through hallucinated functions, misused parameters, and mishandled result tables. We present PowerCodeBench, a parameterised benchmark generator released as a frozen 2,000-task suite for pandapower, and a deployment-time workflow that requires no weight updates. Documentation-driven L0-L3 probes produce per-model API profiles for diagnosis, model comparison, documentation allocation, and backend calibration. A query-side demand estimator selects layered API evidence before generation, while execution feedback routes targeted repair. Across ten open-weight LLMs (1.5B-480B) and four mid-tier APIs, the validation-enabled workflow raises scalar-match accuracy by 32-56 percentage points after up to three repair rounds relative to an unassisted first pass, for every model of at least 7B and every API. Open-weight models in the 70B-120B range reach the four-vendor mid-tier accuracy range under matched no-tool conditions. Selective injection approaches the full-layer reference using 41% of its prompt tokens. Among model-item pairs passing numerical checks under both workflows, engineering review confirms the requested analysis in 88% of full-workflow outputs versus 66% under plain repair. Round-0 pilots on OpenDSS and PyPSA motivate staged onboarding from broad retrieval at cold start to calibrated selective injection. Measured throughput, latency, energy, and allocated GPU memory establish a practical on-premise serving envelope.

Abstract

Agentic Code Generation

Explore similar work

Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation

LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications

RestoreBench: Can AI Agents Restore Power Flow Convergence?