Controlled Comparison of Machine Learning Models for Fault Classification and Localization in Power System Protection

This paper presents a controlled comparison of machine learning models for fault classification (FC) and fault localization (FL) in power systems, utilizing a common electromagnetic transient dataset with decision windows of 10-50 ms. The top-performing nonlinear models for FC achieve F1 scores exceeding 0.98 at 10 ms, while FL models attain a stable localization error of approximately 10% of normalized line length, highlighting the importance of decision timing and topology in model performance. These results establish a standardized reference for evaluating machine learning approaches in power system protection tasks, crucial for practitioners aiming to enhance reliability in modern, complex power networks.