LLM-Driven Transient Stability Assessment: From Automated Simulation to Neural Architecture Design

TL;DR

This paper introduces an LLM-based automated workflow for power system transient stability assessment, combining scenario generation, model design, and optimization, achieving high accuracy and real-time performance on the IEEE 39-bus system.

Contribution

It presents a novel LLM-driven framework that automates TSA tasks from scenario creation to neural network design, enhancing efficiency and accuracy over traditional manual methods.

Findings

Achieves 93.71% accuracy with 4.78M parameters on IEEE 39-bus system

Maintains real-time inference latency under 1 millisecond

Outperforms manually designed DenseNet in accuracy and efficiency

Abstract

This paper presents an LLM-driven, end-to-end workflow that addresses the lack of automation and intelligence in power system transient stability assessment (TSA). The proposed agentic framework integrates large language models (LLMs) with a professional simulator (ANDES) to automatically generate and filter disturbance scenarios from natural language, and employs an LLM-driven Neural Network Design (LLM-NND) pipeline to autonomously design and optimize TSA models through performance-guided, closed-loop feedback. On the IEEE 39-bus system, the LLM-NND models achieve 93.71% test accuracy on four-class TSA with only 4.78M parameters, while maintaining real-time inference latency (less than 0.95 ms per sample). Compared with a manually designed DenseNet (25.9M parameters, 80.05% accuracy), the proposed approach jointly improves accuracy and efficiency. Ablation studies confirm that the synergy among domain-grounded retrieval, reasoning augmentation, and feedback mechanisms is essential for robust automation. The results demonstrate that LLM agents can reliably accelerate TSA research from scenario generation and data acquisition to model design and interpretation, offering a scalable paradigm that is readily extensible to other power system tasks such as optimal power flow, fault analysis, and market operations.