Disturbance Classification Utilizing Wavelet and Multi-class Support Vector Machines

With extensive use of power electronic devices and microprocessor-based systems requiring high quality of electric power, power quality has become a major concern. This paper presents a novel classification method of power quality disturbance problems in electric power systems. To improve the electric power quality, sources of disturbances must be known and controlled. This paper proposes a method of power quality disturbance classification using wavelet transform and multi-class support vector machines. Wavelet transform is mainly used to extract features of power quality disturbances; and support vector machine is mainly used to construct a multi-class classifier which can classify power quality disturbances according to the extracted features. Results of simulation and analysis demonstrate that this proposed approach can achieve higher classification accuracy.