Power Quality Event Classification Using Wavelets, Decision Trees and SVM Classifiers

Abstract

AbstractRecently the usage of voltage-sensitive devices around the world is growing rapidly. These devices are not ideal and may get affected by Power Quality (PQ) events such as Sag, Swell, Harmonics, and Interruptions, etc. In IoT applications, failure of these sensitive devices may cause serious damages. Existing methods classify the disturbances 90–97% accurately with a large feature set. To avoid complexity, this paper deals with the classification of PQ events with a set of wavelet decomposed & direct signal features such as Shannon entropy, mean energy, and total harmonic distortion (THD), etc. Machine Learning (ML) approaches such as Decision Tree (DT) and Support Vector Machine (SVM) classifiers are used for classification. By considering the different training rates, the performance analysis is carried out. Simulation results indicate the supremacy of the proposed DT & SVM classifiers when compared with the already existing methods.KeywordsPQ eventsWTDecision treesSVM classifiers