A hybrid approach for detection and classification of power quality disturbances

With the advances of technologies, high quality of electric power is in demand. The power quality (PQ) disturbances occurred in the power system may cause voltage and current deviation from their nominals, which can result in serious damages or equipment malfunctions. Therefore, efficient detection and classification of PQ disturbances in a transmission system is of great importance for maintaining reliable system operation. This paper presents a hybrid approach to classify PQ disturbances by using support vector machine (SVM), discrete wavelet transform (DWT), and discrete Fourier transform (DFT) to extract features from a good number of actual measured PQ events occurred in a transmission system. Results show that the proposed method can provide fast and accurate classifications of the measured PQ events.