Power Quality Disturbance Identification Using Improved Particle Swarm Optimizer and Support Vector Machine

This paper proposes an approach for identification of power quality (PQ) disturbances based on improved particle swarm optimizer and support vector machine. In order to identify the PQ disturbances more rapidly and precisely, mathematical morphology (MM) which is an excellent analysis tool in processing the shape of waveforms with non-linear signals is used to filter out noise in the signals. To improve the classification accuracy of support vector machine (SVM), improved particle swarm optimizer (IPSO) is applied to optimize its parameters. Simulation studies have been conducted to test the performance of the proposed approach and the results compared with SVM, PSO-SVM and GA-SVM have demonstrated its validity.