Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.07010 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909025598177280 |
|---|---|
| author | Zhou, Tianxin Li, Xiang Lu, Haibing |
| author_facet | Zhou, Tianxin Li, Xiang Lu, Haibing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07010 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention Zhou, Tianxin Li, Xiang Lu, Haibing Machine Learning 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. |
| title | Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.07010 |