IDENTIFICATION OF. POWER QUALITY DISTURBANCE USING NEURAL NETWORK

Abstract

Electric power quality has become an important issue in electrical system operation, which leads to the comprehensive data collection of associated disturbance by utilities Computerized classification and characterization of the data is quite in comprehending the voluminous quantities of recorded data. In this work an approach is presented to detect, identify the power quality events. This method use discrete wavelet transform as a tool for crunching the voluminous data that are being recorded by the. utilities. The signal is decomposed throught wavelet transform and any change on the smoothness or pattern of the signal is detected and located at the finer wavelet transform resolution levels. This forms the detection stage of the process. In the next stage, the coefficient of discrete wavelet transform coefficient for various type of disturbance shall be used as input pattern to train the neural network using back propagation algorithum, to classify the type of event