Feature Selection for Fault Prediction in Distribution Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kordowich, Georg, Oelhaf, Julian, Bayer, Siming, Maier, Andreas, Kereit, Matthias, Jaeger, Johann
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917362917179392
author Kordowich, Georg
Oelhaf, Julian
Bayer, Siming
Maier, Andreas
Kereit, Matthias
Jaeger, Johann
author_facet Kordowich, Georg
Oelhaf, Julian
Bayer, Siming
Maier, Andreas
Kereit, Matthias
Jaeger, Johann
contents While conventional power system protection isolates faulty components only after a fault has occurred, fault prediction approaches try to detect faults before they can cause significant damage. Although initial studies have demonstrated successful proofs of concept, development is hindered by scarce field data and ineffective feature selection. To address these limitations, this paper proposes a surrogate task that uses simulation data for feature selection. This task exhibits a strong correlation (r = 0.92) with real-world fault prediction performance. We generate a large dataset containing 20000 simulations with 34 event classes and diverse grid configurations. From 1556 candidate features, we identify 374 optimal features. A case study on three substations demonstrates the effectiveness of the selected features, achieving an F1-score of 0.80 and outperforming baseline approaches that use frequency-domain and wavelet-based features.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25274
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Feature Selection for Fault Prediction in Distribution Systems
Kordowich, Georg
Oelhaf, Julian
Bayer, Siming
Maier, Andreas
Kereit, Matthias
Jaeger, Johann
Systems and Control
While conventional power system protection isolates faulty components only after a fault has occurred, fault prediction approaches try to detect faults before they can cause significant damage. Although initial studies have demonstrated successful proofs of concept, development is hindered by scarce field data and ineffective feature selection. To address these limitations, this paper proposes a surrogate task that uses simulation data for feature selection. This task exhibits a strong correlation (r = 0.92) with real-world fault prediction performance. We generate a large dataset containing 20000 simulations with 34 event classes and diverse grid configurations. From 1556 candidate features, we identify 374 optimal features. A case study on three substations demonstrates the effectiveness of the selected features, achieving an F1-score of 0.80 and outperforming baseline approaches that use frequency-domain and wavelet-based features.
title Feature Selection for Fault Prediction in Distribution Systems
topic Systems and Control
url https://arxiv.org/abs/2603.25274