Localization and Classification of Power Quality Disturbances using Maximal Overlap Discrete Wavelet Transform and Data Mining based Classifiers

摘要

This paper has proposed the time-series based maximal overlap discrete wavelet transform (MODWT) technique for detection and localization of different types of power quality (PQ) disturbances. Ten types of different PQ events of the voltage signal such as sag, swell, interruption, harmonic, spike, notch etc. are analyzed with the aforementioned wavelet transform (WT). Each of the signal is decomposed up to fourth level with the MODWT. The co-efficients of MODWT decomposition are further used for feature extraction which are the input to the classifiers like Support Vector Machine (SVM) and Decision Tree (DT). For the detection of the disturbances, the signals are decomposed up to four finer levels whereas for the classification, decomposition is carried out up to seventh finer levels.