Comparative analysis of input parameters using wavelet transform for voltage sag disturbance classification

Voltage sag is one of the major power quality disturbance today. Significant causes of voltage sag include power system fault, starting of induction motor and energizing of transformer. This paper focus on a comparative analysis carried out to determine the best input parameters to be employed in support vector machine (SVM) method for voltage sag cause classification. Wavelet transform is carried out to extract the feature of these voltage sags which are used as the input to the SVM. Two different types of inputs used, namely the energy level and the min-max values of the wavelet. Comparisons between these input parameters are made to determine the best method which give the best prediction values. Training and testing data based on the standard IEEE 30 bus distribution system are simulated using PSCAD software. The results show that the performance of the min-max wavelet values as the input to the SVM is superior than the energy level input in term of accuracy and computational time.