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

Abstract

Abstract:In this paper, a novel perturbed particle swarm optimization (PPSO) algorithm is investigated to improve the performance of a support vector machine (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 (PC-PSO), perturbed T-PSO (PT-PSO), and perturbed K-PSO (PK-PSO). For the purpose of fault diagnosis, the timedomain reflectometry (TDR) method with pseudorandom binary sequence (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.

Research on the Diagnosis of Distribution Network Fault Data Using a Fault Prediction Model

“…The power system generates a huge amount of data every second, and with the development of information technology, methods such as artificial intelligence have been increasingly used in the diagnosis of fault data [1], through which valuable content can be identified from fault data to achieve prediction faults. Thom et al [2] designed a support vector machine (SVM)-based method for shortcircuit faults in power distribution systems. They improved the diagnostic performance of the SVM method by an improved particle swarm algorithm (IPSO) and demonstrated the reliability of the method by testing on a bidirectional radial distribution network.…”