MoE-GraphSAGE-Based Integrated Evaluation of Transient Rotor Angle and Voltage Stability in Power Systems

2025-11-05

AI Summary

The increasing penetration of renewable energy sources and power electronic devices complicates transient stability assessment in modern power systems, where conventional methods struggle to balance accuracy and computational efficiency. To address this, this paper proposes a unified angle–voltage stability analysis framework based on graph neural networks (GNNs). The method innovatively integrates GraphSAGE to capture spatiotemporal topological dynamics of the grid, employs a Mixture-of-Experts (MoE) mechanism to adaptively model diverse instability patterns, and incorporates a gating mechanism for joint multi-task evaluation and adaptive instability mode identification. Validated on the IEEE 39-bus system, the proposed model achieves significantly improved accuracy and computational efficiency compared to existing approaches, demonstrating strong potential for real-time online applications. This work establishes a scalable and interpretable paradigm for intelligent transient stability assessment in future power systems.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The large-scale integration of renewable energy and power electronic devices has increased the complexity of power system stability, making transient stability assessment more challenging. Conventional methods are limited in both accuracy and computational efficiency. To address these challenges, this paper proposes MoE-GraphSAGE, a graph neural network framework based on the MoE for unified TAS and TVS assessment. The framework leverages GraphSAGE to capture the power grid's spatiotemporal topological features and employs multi-expert networks with a gating mechanism to model distinct instability modes jointly. Experimental results on the IEEE 39-bus system demonstrate that MoE-GraphSAGE achieves superior accuracy and efficiency, offering an effective solution for online multi-task transient stability assessment in complex power systems.

Problem

• Assessing transient rotor angle and voltage stability in complex power systems
• Overcoming accuracy and computational limitations of conventional assessment methods
• Modeling distinct instability modes through unified graph neural network framework

Innovation

• MoE-GraphSAGE framework for unified stability assessment
• GraphSAGE captures spatiotemporal grid topological features
• Multi-expert networks with gating model instability modes