Scalability and Sample Efficiency Analysis of Graph Neural Networks for Power System State Estimation

TL;DR

This paper evaluates the scalability and sample efficiency of graph neural networks for power system state estimation, demonstrating high accuracy and efficiency across different system sizes and training data volumes.

Contribution

It provides a comprehensive analysis of GNN-based state estimators, highlighting their scalability and data efficiency in power system applications.

Findings

GNN-based estimator achieves high accuracy.

Demonstrates scalability in memory and inference time.

Efficient with varying training set sizes.

Abstract

Data-driven state estimation (SE) is becoming increasingly important in modern power systems, as it allows for more efficient analysis of system behaviour using real-time measurement data. This paper thoroughly evaluates a phasor measurement unit-only state estimator based on graph neural networks (GNNs) applied over factor graphs. To assess the sample efficiency of the GNN model, we perform multiple training experiments on various training set sizes. Additionally, to evaluate the scalability of the GNN model, we conduct experiments on power systems of various sizes. Our results show that the GNN-based state estimator exhibits high accuracy and efficient use of data. Additionally, it demonstrated scalability in terms of both memory usage and inference time, making it a promising solution for data-driven SE in modern power systems.