Classi cations of disturbances using wavelet transform and support vectormachine

Abstract

This paper proposes a new method to detect and classify all kinds of faults, capacitor switching, and loadswitching in a power system network based on wavelet transform and support vector machines (SVMs). In this regard,a sample of a power system is simulated via MATLAB/Simulink, and by reading the voltage of the point of commoncoupling and using the wavelet transform, the differences of the outputs of the wavelet transform are investigated. TheSVM approach is employed to distinguish the type of the transient (capacitor switching, fault, and/or load switching)in use for the high level outputs of the wavelet transform. Similar to neural networks, this method, which is basedon learning, is considered as a proper tool for data classi cation. The results of simulations demonstrate that thecombination of wavelet transform and SVM recognizes the type of the transient correctly and effectively as well asdistinguishes capacitor switching and load switching events from all kinds of faults such as three-phase-to-earth fault,phase-to-phase fault, two-phase-to-earth fault, and single-phase-to-earth fault. In the end, the accuracy of the presentedapproach is evaluated and the simulation results are proposed for different attributes of transients in the power systemnetwork.