Topology-Aware Graph Neural Network-based State Estimation for PMU-Unobservable Power Systems

TL;DR

This paper introduces a graph neural network-based state estimation method for power systems that effectively handles topology changes, data loss, and non-Gaussian noise, outperforming traditional and existing learning-based approaches.

Contribution

It presents a novel deep geometric learning framework using GNNs that adapts to topology changes and data loss in power system state estimation.

Findings

Outperforms traditional optimization-based methods.

Handles topology changes and data loss effectively.

Demonstrates robustness against non-Gaussian noise.

Abstract

Traditional optimization-based techniques for time-synchronized state estimation (SE) often suffer from high online computational burden, limited phasor measurement unit (PMU) coverage, and presence of non-Gaussian measurement noise. Although conventional learning-based models have been developed to overcome these challenges, they are negatively impacted by topology changes and real-time data loss. This paper proposes a novel deep geometric learning approach based on graph neural networks (GNNs) to estimate the states of PMU-unobservable power systems. The proposed approach combines graph convolution and multi-head graph attention layers inside a customized end-to-end learning framework to handle topology changes and real-time data loss. An upper bound on SE error as a function of topology change is also derived. Experimental results for different test systems demonstrate superiority of the proposed customized GNN-SE (CGNN-SE) over traditional optimization-based techniques as well as conventional learning-based models in presence of topology changes, PMU failures, bad data, non-Gaussian measurement noise, and large system implementation.