Robustness of Spatio-temporal Graph Neural Networks for Fault Location in Partially Observable Distribution Grids

2026-04-22

AI Summary

This study addresses the challenge of fault location in sparsely measured, partially observable distribution networks. The authors propose a “measurement-only” graph construction strategy combined with a spatiotemporal graph neural network (STGNN) to systematically compare modeling performance between full-topology graphs and subgraphs comprising only measurement nodes. The proposed architecture integrates GraphSAGE with an enhanced GATv2 mechanism and is evaluated on the IEEE 123-bus feeder. Experimental results demonstrate that the method achieves up to an 11-percentage-point improvement in F1 score over RNN-based baselines, reduces training time by a factor of six, and exhibits greater stability, thereby significantly enhancing both the efficiency and robustness of fault location in distribution systems.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Distributed Search

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: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Fault location in distribution grids is critical for reliability and minimizing outage durations. Yet, it remains challenging due to partial observability, given sparse measurement infrastructure. Recent works show promising results by combining Recurrent Neural Networks (RNNs) and Graph Neural Networks (GNNs) for spatio-temporal learning. Still, many modern GNN architectures remain untested for this grid application, while existing GNN solutions have not explored GNN topology definitions beyond simply adopting the full grid topology to construct the GNN graph. We address these gaps by (i) systematically comparing a newly proposed graph-forming strategy (measured-only) to the traditional full-topology approach, and (ii) introducing STGNN (Spatio-temporal GNN) models based on GraphSAGE and an improved Graph Attention (GATv2), for distribution grid fault location; (iii) benchmarking them against state-of-the-art STGNN and RNN baselines on the IEEE 123-bus feeder. In our experiments, all evaluated STGNN variants achieve high performance and consistently outperform a pure RNN baseline, with improvements up to 11 percentage points F1. Among STGNN models, the newly explored RGATv2 and RGSAGE achieve only marginally higher F1 scores. Still, STGNNs demonstrate superior stability, with tight confidence intervals (within +/- 1.4%) compared to the RNN baseline (up to +/- 7.5%) across different experiment runs. Finally, our proposed reduced GNN topology (measured-only) shows clear benefits in both (i) model training time (6-fold reduction) and (ii) model performance (up to 11 points F1). This suggests that measured-only graphs offer a more practical, efficient, and robust framework for partially observable distribution grids.

Problem

• fault location
• distribution grids
• partial observability
• spatio-temporal graph neural networks
• GNN topology

Innovation

• Spatio-temporal Graph Neural Networks
• measured-only topology
• GraphSAGE
• GATv2
• fault location