Machine learning improves fault detection in electrical power grids
A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids
Machine Learning
Summary
Detecting faults like short circuits quickly in electrical grids is critical for safety and reliable power delivery. Traditional systems use fixed rules that may not handle newer challenges from renewable energy sources well. The authors tested different machine learning models to detect faults and identify problem lines within just 10 milliseconds, which is very fast. Their best model was very accurate and worked quickly enough for real-time use.
What this means in practice
- •For power grid operators: Implement fast and accurate machine learning models to detect and isolate faults, improving grid safety and reducing outage times.
- •For smart grid technology developers: Incorporate tested ML-based fault detection algorithms into protective devices to enhance real-time monitoring and fault management.
Authors
Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro, Tomás Arias-Vergara, Andreas Maier, Johann Jäger, Siming Bayer
Abstract
The integration of renewable energy sources into the electrical grid introduces complex challenges in fault detection and coordination of grid recovery mechanisms. Traditional relay protection systems, which operate based on static rules and predefined thresholds, are inadequate for addressing these challenges, particularly in detecting and isolating faults such as short circuits. Consequently, the conventional methodologies applied to electrical network protection frequently fail to achieve optimal performance in fault detection, especially in terms of adherence to safety standards and the selective limitation of damage. Recent research indicates that machine learning (ML)-based approaches can effectively tackle these issues; however, variations in grid configurations and analysis windows have impeded consistent comparative assessments. In this study, we assess the efficacy of various ML models in detecting electrical faults and pinpointing defective transmission lines within a 10 ms measurement interval - a critical time-frame for real-time operational viability, for the first time. The most effective model attained an F1 score of 0.991 +/- 0.018 and demonstrated a processing time of 0.342ms +/- 0.509ms.