Identifying Power Quality Disturbances in Real Time Using Incremental Wavelet Decomposition and Least Square Support Vector Machine

Power quality disturbances identification is the important procedure for improving power quality, and real time application has actual value. An efficient method for power quality disturbances identification is presented. Wavelet decomposition is used for extracting features of various disturbances, and least square support vector machine is used for classifying the disturbances. For real time application, sliding window and incremental algorithms for wavelet decompositions are used. This method can identify different disturbances in high accuracy and less time. Simulation experiment using several typical disturbances is finished, and the experimental results show effectiveness of proposed method.