Generalizable Graph Neural Networks for Robust Power Grid Topology Control

2025-01-13

AI Summary

To address insufficient topological control stability and poor generalization to out-of-distribution (OOD) anomalous operating conditions under energy transition, this paper proposes a novel topology control method based on heterogeneous graph neural networks (Hetero-GNNs). Unlike conventional homogeneous graph modeling—which overlooks bus-type heterogeneity and thus induces information asymmetry—our approach introduces the first purely GNN-based architecture with a physics-informed heterogeneous graph representation, explicitly modeling multi-type nodes (e.g., buses, branches, switches) and their heterogeneous relations. Experiments demonstrate that the proposed method achieves state-of-the-art classification accuracy and real-time performance on in-distribution tasks. Moreover, compared to homogeneous GNNs and fully connected networks, it exhibits significantly enhanced robustness under OOD grid scenarios, empirically validating that heterogeneous structural modeling fundamentally improves generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The energy transition necessitates new congestion management methods. One such method is controlling the grid topology with machine learning (ML). This approach has gained popularity following the Learning to Run a Power Network (L2RPN) competitions. Graph neural networks (GNNs) are a class of ML models that reflect graph structure in their computation, which makes them suitable for power grid modeling. Various GNN approaches for topology control have thus been proposed. We propose the first GNN model for grid topology control that uses only GNN layers. Additionally, we identify the busbar information asymmetry problem that the popular homogeneous graph representation suffers from, and propose a heterogeneous graph representation to resolve it. We train both homogeneous and heterogeneous GNNs and fully connected neural networks (FCNN) baselines on an imitation learning task. We evaluate the models according to their classification accuracy and grid operation ability. We find that the heterogeneous GNNs perform best on in-distribution networks, followed by the FCNNs, and lastly, the homogeneous GNNs. We also find that both GNN types generalize better to out-of-distribution networks than FCNNs.

Problem

• Power Network Stability
• Energy Adaptation
• Grid Congestion Management

Innovation

• Graph Neural Networks
• Power Network Control
• Enhanced Grid Representation