Detection and classification of power quality disturbances: Using curvelet transform and support vector machines

Abstract

Power quality has become prime criteria in modern scenario of power system analysis. PQD effect serious problems in the reliability, security and saving of power system network. In order to improve electric power quality events, we propose a new scheme based on curvelet transform and support vector machine. This article presents a novel approach to recognize and classification of power quality disturbances using Curve let transform and support vector machines. Curve let transform is used to extract features of power quality disturbances and support vector machine (SVM) is used to create a multi-class classifier that can classify power quality disturbances according to the extracted features. The objective of this paper is to present a new method for automatically identifying, localizing and classifying various types of power quality disturbances. A variety of transient events, such as voltage sag, swell, interruption, harmonic, transient, sag with harmonic, swell with harmonic, and gleam are tested. Simulation results show that the proposed method can identify and classify different power quality signals, effectively, accurately and reliably, even under noisy conditions and achieve higher identification rate, much better convergence property and less training time compared with the method based on SVM.