DeVLearn: A Deep Visual Learning Framework for Localizing Temporary Faults in Power Systems

TL;DR

DeVLearn is a deep learning framework that transforms PMU time series data into images, enabling effective fault localization in power systems through advanced visual and latent space analysis.

Contribution

The paper introduces DeVLearn, a novel image embedding and deep learning approach for localizing faults in power systems using PMU data, inspired by computer vision techniques.

Findings

DeVLearn accurately separates fault locations in a 2D latent space.

The framework effectively uses RP images and VAE for fault classification.

Results demonstrate high clustering quality for different fault sites.

Abstract

Frequently recurring transient faults in a transmission network may be indicative of impending permanent failures. Hence, determining their location is a critical task. This paper proposes a novel image embedding aided deep learning framework called DeVLearn for faulted line location using PMU measurements at generator buses. Inspired by breakthroughs in computer vision, DeVLearn represents measurements (one-dimensional time series data) as two-dimensional unthresholded Recurrent Plot (RP) images. These RP images preserve the temporal relationships present in the original time series and are used to train a deep Variational Auto-Encoder (VAE). The VAE learns the distribution of latent features in the images. Our results show that for faults on two different lines in the IEEE 68-bus network, DeVLearn is able to project PMU measurements into a two-dimensional space such that data for faults at different locations separate into well-defined clusters. This compressed representation may then be used with off-the-shelf classifiers for determining fault location. The efficacy of the proposed framework is demonstrated using local voltage magnitude measurements at two generator buses.