Contribution to Distribution System Automation for Diagnosis of Power Quality Disturbances Using Wavelet Transform And RBF Networks

Contribution to Distribution System Automation for Diagnosis of Power Quality Disturbances Using Wavelet Transform And RBF Networks

Abstract: in this paper a new approach for detection and classification of wide variety range (15 types) o f power quality violation based on IEEE 1159 standard is presented. For this purpose wavelet multiresolution signal analysis is used to de-noise and then decompose the signal of power quality event to extract its useful information. After this an optimal vector of computed features is selected and adopted in learning radial basis function (RBF) network classifier. This vector represents a distinctive property of studied power quality events with minimum amount of needed training data. RBF structure effectively reduces training time of the network. The proposed classifier has significantly improved automatically diagnosis efficiency of power quality disturbances in distribution system. Simulation results with low error rate confirm this capability.