A scoping review of machine learning applications in power system protection and disturbance management

The integration of renewable and distributed energy resources has fundamentally reshaped modern power systems, challenging conventional protection schemes built around centralized generation. This scoping review synthesizes recent literature on machine learning (ML) applications in power system protection and disturbance management, following the PRISMA for Scoping Reviews framework. Based on over 100 publications, three key objectives are addressed: (i) assessing the scope of ML research in protection tasks; (ii) evaluating ML performance across diverse operational scenarios; and (iii) identifying methods suitable for evolving grid conditions. Machine learning models often demonstrate high accuracy on simulated datasets; however, their performance under real-world conditions remains insufficiently validated. The existing literature is fragmented, with inconsistencies in methodological rigor, dataset quality, and evaluation metrics. This lack of standardization hampers the comparability of results and limits the generalizability of findings across different applications. To address these challenges, this review introduces a machine learning-oriented taxonomy for protection tasks, resolves key terminological inconsistencies, and advocates for standardized reporting practices. It further provides guidelines for comprehensive dataset documentation, methodological transparency, and consistent evaluation protocols, aiming to improve reproducibility and enhance the practical relevance of research outcomes. Critical gaps remain, including the scarcity of real-world validation, insufficient robustness testing, and limited consideration of deployment feasibility. Future research should prioritize public benchmark datasets, realistic validation methods, and advanced ML architectures. These steps are essential to move ML-based protection from theoretical promise to practical deployment in increasingly dynamic and decentralized power systems. • Machine learning models show high accuracy on simulated data but lack real-world validation. • Studies vary in task scope, dataset use, and evaluation, hindering comparisons. • A unified taxonomy is proposed for protection tasks in power system research. • Guidelines for dataset reporting and reproducibility support future benchmarks.