Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids

TL;DR

This paper explores the application of graph neural networks to electrical power grids, demonstrating their robustness and unique properties in real-world scenarios, and highlighting the importance of domain-specific graph characteristics.

Contribution

It introduces power grid-specific graph datasets, analyzes their properties, and empirically studies GNN performance on real-world power grid state estimation tasks.

Findings

GNNs are more robust to noise with up to 400% lower error.

Deep GNNs with up to 13 layers outperform shallow models.

Electrical grid properties prevent the over-smoothing phenomenon.

Abstract

The application of graph neural networks (GNNs) to the domain of electrical power grids has high potential impact on smart grid monitoring. Even though there is a natural correspondence of power flow to message-passing in GNNs, their performance on power grids is not well-understood. We argue that there is a gap between GNN research driven by benchmarks which contain graphs that differ from power grids in several important aspects. Additionally, inductive learning of GNNs across multiple power grid topologies has not been explored with real-world data. We address this gap by means of (i) defining power grid graph datasets in inductive settings, (ii) an exploratory analysis of graph properties, and (iii) an empirical study of the concrete learning task of state estimation on real-world power grids. Our results show that GNNs are more robust to noise with up to 400% lower error compared to baselines. Furthermore, due to the unique properties of electrical grids, we do not observe the well known over-smoothing phenomenon of GNNs and find the best performing models to be exceptionally deep with up to 13 layers. This is in stark contrast to existing benchmark datasets where the consensus is that 2 to 3 layer GNNs perform best. Our results demonstrate that a key challenge in this domain is to effectively handle long-range dependence.