Robust and Interpretable Graph Neural Networks for Power Systems State Estimation

TL;DR

This paper evaluates different Graph Neural Network architectures for power system state estimation, highlighting the interpretability and performance trade-offs, and proposing mechanisms to improve learning based on grid topology and data availability.

Contribution

It introduces an interpretable GNAN architecture with edge-conditioned message passing and benchmarks it against GAT, advancing understanding of GNNs in power system state estimation.

Findings

GNAN is more interpretable but less accurate than GAT.

Edge attention mechanisms help incorporate distant node information.

Performance depends on grid topology and measurement data availability.

Abstract

This study analyzes Graph Neural Networks (GNNs) for distribution system state estimation (DSSE) by employing an interpretable Graph Neural Additive Network (GNAN) and by utilizing an edge-conditioned message-passing mechanism. The architectures are benchmarked against the standard Graph Attention Network (GAT) architecture. Multiple SimBench grids with topology changes and various measurement penetration rates were used to evaluate performance. Empirically, GNAN trails GAT in accuracy but serves as a useful probe for graph learning when accompanied with the proposed edge attention mechanism. Together, they demonstrate that incorporating information from distant nodes could improve learning depending on the grid topology and available data. This study advances the state-of-the-art understanding of learning on graphs for the state estimation task and contributes toward reliable GNN-based DSSE prediction technologies.