A fault location and protection scheme for distribution systems in presence of dg using MLP neural networks

Abstract

Traditional electric distribution systems are radial in nature. These networks are protected by very simple protection devices such as over-current relays, fuses, and re-closers. Recent trends in distributed generation (DG) and its useful advantages perfectly can be achieved while the relevant concerns are deliberately taken into account. For example, penetration of DG disturbs the radial nature of conventional distribution networks. Therefore, protection coordination will be changed in some cases, and in some other cases it will be lost. The penetration of DG into distribution networks reinforces the necessity of designing new protection systems for these networks. One of the main capabilities that can improve the efficiency of new protection relays in distribution systems is exact fault locating. In this paper, a novel fault location and protection scheme has been presented to provide the distribution networks with DG. The suggested approach is able to determine the accurate type and location of faults using MLP neural networks. As case study, the proposed scheme has been assessed using a MATLAB based developed software and DIgSILENT Power Factory 13.2 on a sample distribution network.