Classification of power quality events using extreme learning machine

Industrial plants and residential areas need to utilize electrical energy effectively. For this purpose smart grids were performed within power system voltage and current signals are processed and monitored in advanced. Thus controller systems provide such solutions that will keep the grid sustainability both faulty and normal conditions. In this study, single phase voltage data set consists of power quality events is composed in software and classified by an intelligent classifier. Distinctive features are extracted by discrete wavelet transform method. Feature vector size reduction is held via entropy values determining of discrete wavelet details. Extreme learning machine is used as classifier and its advantages in performance are evaluated with conventional artificial neural networks.