Review of Detection and Classification of Power Quality Disturbances Using Machine Learning and Deep Learning Methods

Power quality disturbances (PQDs) present major challenges to the stable operation of electricity systems. Traditional methods for detecting and classifying PQDs rely on manual analysis and predefined rules, which can be time-consuming, subjective, and unable to manage complex patterns. Researchers have investigated the application of machine learning (ML) and deep learning (DL) techniques to the field of power quality (PQ) analysis in the context of their development. This article provides a summary of recent advances in the detection and classification of PQDs using ML and DL methods. Various algorithms and architectures, such as Support vector machines (SVM), neural networks (NN), convolutional neural networks (CNN), etc., are discussed. The paper explores a review of the detection and classification of PQDs Using ML and DL Methods. In addition, challenges and future directions in the field are presented to direct future research in this important domain. This review demonstrates the potential for machine learning and deep learning to improve the detection and classification of PQDs, resulting in more effective power quality management and enhanced system reliability.