cs.LGNov 13, 2026

Protection-Oriented Assessment of Machine Learning-Based Fault Detection in Power Systems

Authors: Julian Oelhaf, Georg Kordowich, Changhun Kim, Christian Bergler, Andreas Maier, Johann Jäger, Siming Bayer

Organizations: Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Institute of Electrical Energy Systems, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Department of Electrical Engineering, Media and Computer Science, Ostbayerische Technische Hochschule Amberg-Weiden, Amberg, Germany

Abstract

Machine learning (ML)-based fault detectors are increasingly proposed for power system protection, yet aggregate metrics can obscure the consequences of false and missed trips. We present a protection-oriented assessment of three ML detectors and a sequence-current reference on PROTECT-90, comprising 9,022 simulated fault episodes on a 90 kV double-circuit line. The assessment combines five window conditions, causal window-end labelling, episode-grouped cross-validation, and operating-point selection under a fixed security budget. It reports security, dependability, detection timing, decision margins, and episode-level nuisance assertions. Gradient-boosted trees, a convolutional neural network, and logistic regression achieve AUC-ROC values above 0.999, yet at a security budget of 10−310^{-3} their developed-fault missed-trip rates range from 0.007% to 1.99%. Post-clearing false-trip rates of approximately 0.12-0.16% per window coexist with nuisance assertions in 11.3-19.1% of episodes. Among the analysed physical descriptors, missed trips are most consistently associated with higher fault resistance within the sampled range. An analytical current proxy suggests a fault-current gradient only partly reproduced by waveform-derived current (rank correlation 0.62). No single topology state or faulted phase consistently dominates within the sampled domain. Because PROTECT-90 contains fault episodes only, security is assessed on pre-fault and post-clearing windows rather than independent non-fault disturbances.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Standardized Framework for Machine Learning in Power System Protection

    Aug 20, 2026Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro +4Power System Fault DiagnosisPower Systems

  2. Characterizing Cross-Relay Generalization Failure in Machine Learning-Based Power System Protection

    Oct 20, 2026Nithin Pradeep Nadayil Kizhakkethil, Julian Oelhaf, Christian Bergler +2Neural Network GeneralizationPower System Fault Diagnosis

  3. A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids

    Sep 15, 2026Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro +4Power System Fault DiagnosisFault Localization