A Comparative Study Of Feature Extraction Techniques For Power Disturbances Pattern Recognition Using SVMs

The rapid increase in computer technology and the availability of large scale power quality monitoring data should now motivate distribution network service. providers to attempt to extract information that may otherwise remain hidden within the recorded data. Such information may be critical for identification and diagnoses of power quality disturbance problems, prediction of system abnormalities or failure, and alarming of critical system situations. Data mining tools are an obvious candidate for assisting in such analysis of large scale power quality monitoring data. Firstly feature extraction technique is employed to extract features from raw power quality data. Finally support vector machine is used as a data mining tool to classify the extracted features into different disturbance type. Feature extraction technique should be efficient for the effective functioning of data mining tool. In this work, two methods of feature extraction for Power quality data mining are studied: Discrete Wavelet Transform (DWT) and S-Transform (Phase Corrected DWT). The S-transform requires less number of features as compared to wavelet based.Dr.Sivanthi Aditanar College of Engineering, Tiruchendur, India (phone: 9486453814; e-mail r.ahilame@gmail.com). Dr. E. Suthakaran, is with Pondichery Engineering College, Pondichery(email: karan_ mahalingam @ yahoo.com). Dr.Sivanthi Aditanar College of Engineering, Tiruchendur, India (e-mail: s_monimala@yahoo.com).approach for the identification of PQ events. Since the proposed feature extraction technique can reduce the dimensionality of the disturbance signal to a great extent without losing its original property, less memory space and learning SVM time are required for classification.