Classification of power quality disturbances using wavelet transform and K-nearest neighbor classifier

This paper proposes a new method to classify power quality disturbances using wavelet transform and K-nearest neighbor classifier. New features of power quality disturbances are extracted from discrete wavelet transform then using K-nearest neighbor classifier to classify these disturbances according to the features. Block diagram of the proposed method has been shown in this paper. Performance of the proposed method is trained and verified with power quality disturbances generated by Matlab software. The classification accuracy for these disturbances has been presented and shows that the proposed method is doing well in classifying these types of power quality disturbances.