GNN with Auxiliary Learning for PMU Data Reconstruction

This paper addresses the critical problem of missing data in wide-area measurement systems (WAMS) used in power grids. The proposed method, leveraging a Graph Neural Network (GNN) with auxiliary task learning (ATL), aims to improve the reconstruction of missing PMU data, overcoming limitations of existing methods such as inadaptability to concept drift, poor robustness under high missing rates, and reliance on full system observability. The use of a K-hop GNN and an auxiliary GNN to exploit low-rank properties of PMU data are key innovations. The paper's focus on robustness and self-adaptation is particularly important for real-world applications.

• •Proposes a GNN-based method for reconstructing missing PMU data in WAMS.
• •Employs auxiliary task learning to improve accuracy and robustness.
• •Addresses limitations of existing methods, such as concept drift and incomplete observability.
• •Demonstrates superior performance under high missing rates.