Fault Detection in Electrical Distribution System using Autoencoders

TL;DR

This paper introduces an anomaly detection method using deep autoencoders, including convolutional autoencoders, to improve fault detection accuracy in electrical power systems, addressing data scarcity and computational efficiency.

Contribution

The paper proposes a novel autoencoder-based fault detection approach that enhances accuracy and reduces training time using convolutional autoencoders for dimensionality reduction.

Findings

Achieved 97.62% accuracy on simulated data

Achieved 99.92% accuracy on public datasets

Demonstrated superior performance over existing methods

Abstract

In recent times, there has been considerable interest in fault detection within electrical power systems, garnering attention from both academic researchers and industry professionals. Despite the development of numerous fault detection methods and their adaptations over the past decade, their practical application remains highly challenging. Given the probabilistic nature of fault occurrences and parameters, certain decision-making tasks could be approached from a probabilistic standpoint. Protective systems are tasked with the detection, classification, and localization of faulty voltage and current line magnitudes, culminating in the activation of circuit breakers to isolate the faulty line. An essential aspect of designing effective fault detection systems lies in obtaining reliable data for training and testing, which is often scarce. Leveraging deep learning techniques, particularly the powerful capabilities of pattern classifiers in learning, generalizing, and parallel processing, offers promising avenues for intelligent fault detection. To address this, our paper proposes an anomaly-based approach for fault detection in electrical power systems, employing deep autoencoders. Additionally, we utilize Convolutional Autoencoders (CAE) for dimensionality reduction, which, due to its fewer parameters, requires less training time compared to conventional autoencoders. The proposed method demonstrates superior performance and accuracy compared to alternative detection approaches by achieving an accuracy of 97.62% and 99.92% on simulated and publicly available datasets.