Anomaly Detection with Machine Learning Algorithms in Large-Scale Power Grids

TL;DR

This paper evaluates various machine learning algorithms for anomaly detection in large-scale power grids, highlighting neural networks' superior performance and the robustness of unsupervised methods.

Contribution

It provides a comparative analysis of ML algorithms for anomaly detection in power grids, emphasizing the effectiveness of neural networks and unsupervised learning.

Findings

Neural networks outperform classical algorithms in anomaly detection.

Unsupervised algorithms are robust against multiple concurrent anomalies.

Contextual nature of anomalies explains performance differences.

Abstract

We apply several machine learning algorithms to the problem of anomaly detection in operational data for large-scale, high-voltage electric power grids. We observe important differences in the performance of the algorithms. Neural networks typically outperform classical algorithms such as k-nearest neighbors and support vector machines, which we explain by the strong contextual nature of the anomalies. We show that unsupervised learning algorithm work remarkably well and that their predictions are robust against simultaneous, concurring anomalies.