An Algorithm for Fault Detection and Identification of Iraqi Distribution Network Using Wavelet-Neural Network Technique

Abstract

Power system restoration plays an important role in power system due to the incident of a fault. This paper presents an algorithm to diagnosis and identify the fault in power system distribution regarding the significant of system reliability and fault occurrence time. This algorithm performs a hybrid wavelet-neural network for an Iraqi distribution feeder. The wavelet transform structure was used as an integrate input to the neural network. The simulation results of a selected feeder at Baghdad city is used to validate the application of the proposed algorithm. From the obtained results it was clear that using the proposed algorithm give a fast and accurate method for fault detection and identification of the Iraqi distribution power system.