Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention

TL;DR

This paper introduces a GRU-gated Graph Attention Network that predicts vulnerable power grid lines and transfers knowledge zero-shot to unseen grids, outperforming traditional baselines.

Contribution

The novel model enables zero-shot transfer of cascading failure predictions across different power grids without retraining.

Findings

Model transfers zero-shot to multiple new grids.

Outperforms established structural and electrical baselines.

Effectively identifies vulnerable transmission lines.

Abstract

Identifying vulnerable transmission lines in power grids before a cascading failure occurs is challenging: existing methods can learn inter-line failure correlations from cascade data, but they are trained and evaluated on a single grid, and transferring the learned knowledge to an unseen grid remains an open problem. We address this by training a single Gated Recurrent Unit (GRU)-gated Graph Attention Network on combined cascading failure data from limited training grids and applying it directly to any unseen grid without retraining. A GRU gate controls what information each node retains or discards at each cascade iteration. Empirical evaluation shows that the model transfers zero-shot to multiple new grids spanning inter-time and inter-domain settings. Using information extracted from the trained model, we consistently identify more vulnerable lines than established structural and electrical baselines.