A Graph Neural Network-Based Approach for Power System Protection

Kordowich G, Oelhaf J, Maier A, Bayer S, Jäger J (2025)

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Publisher: IEEE

City/Town: Kiel

Conference Proceedings Title: PowerTech 2025

Event location: Kiel

Abstract

This paper proposes a novel approach to power system protection using graph neural networks (GNNs), which can detect and locate faults on lines in power grids. For each relay, the GNN processes local measurements as well as measurements from adjacent lines to predict both the faulty line and the exact location
of the fault. The GNN is trained on a diverse set of randomly generated, realistic grid structures, enabling generalization to previously unseen grids without retraining. 

The results of a case study demonstrate the effectiveness of the proposed concept. The GNN-based fault localization outperforms conventional distance protection and communication-based fault locators under noise. Additionally, the concept achieves full line coverage of the primary protection zone of each relay while being
robust to missing measurements. Therefore, the proposed GNN-based protection system has the potential to improve the security and dependability of power system protection, particularly in future multivariate grids.

Authors with CRIS profile

How to cite

APA:

Kordowich, G., Oelhaf, J., Maier, A., Bayer, S., & Jäger, J. (2025). A Graph Neural Network-Based Approach for Power System Protection. In PowerTech 2025. Kiel: Kiel: IEEE.

MLA:

Kordowich, Georg, et al. "A Graph Neural Network-Based Approach for Power System Protection." Proceedings of the IEEE Kiel PowerTech, Kiel Kiel: IEEE, 2025.

BibTeX: Download