A novel perturbed particle swarm optimization-based support vector machine for fault diagnosis in power distribution systems

Authors : Hoang Thi THOM, Cho MINGYUAN, Vu Quoc TUAN

Pages : 518-529

View : 10 | Download : 9

Publication Date : 0000-00-00

Article Type : Research Paper

Abstract :In this paper, a novel perturbed particle swarm optimization insert ignore into journalissuearticles values(PPSO); algorithm is investigated to improve the performance of a support vector machine insert ignore into journalissuearticles values(SVM); for short-circuit fault diagnosis in power distribution systems. In the proposed PPSO algorithm, the velocity of each particle is perturbed whenever the particles strike into a local optimum, in order to achieve a higher quality solution to optimization problems. Furthermore, the concept of proposed perturbation is applied to three variants of PSO, and improved corresponding algorithms are named perturbed C-PSO insert ignore into journalissuearticles values(PC-PSO);, perturbed T-PSO insert ignore into journalissuearticles values(PT-PSO);, and perturbed K-PSO insert ignore into journalissuearticles values(PK-PSO);. For the purpose of fault diagnosis, the time- domain re ectometry insert ignore into journalissuearticles values(TDR); method with pseudorandom binary sequence insert ignore into journalissuearticles values(PRBS); excitation is considered to generate the necessary fault simulation data set. The proposed approaches are tested on a typical two-lateral radial distribution network.
Keywords : Fault diagnosis, particle swarm optimization, power distribution networks support vector machine, time domain re ectometry