Detection of Power Quality Events Using DOST-Based Support Vector Machines

This paper presents a method based on discrete orthogonal S-transform (DOST) and support vector machines (SVM) for detection and classification of power quality events. DOS-transform is mainly used to extract features of power quality events and support vector machines are mainly used to construct a multi-class classifier which can classify power quality events according to the extracted features. Results of simulation and analysis demonstrate that the proposed method can achieve higher correct identification rate, better convergence property and less training time compared with the method based on neural network.