Neural network approach for fault location in unbalanced distribution networks with limited measurements

This paper presents an artificial neural network (ANN) approach for locating faults in distribution systems. Different from the traditional fault section estimation methods, the proposed approach uses only limited measurements. Faults are located according to the impedances of their path using a feed forward neural networks (FFNN). Various practical situations in distribution systems, such as protective devices placed only at the substation, limited measurements available, various types of faults viz., three-phase, line (a, b, c) to ground, line to line (a-b, b-c, c-a) and line to line to ground (a-b-g, b-c-g, c-a-g) faults and a wide range of varying short circuit levels at substation, are considered for studies. A typical IEEE 34 bus practical distribution system with unbalanced loads and with three- and single- phase laterals and a 69 node test feeder with different configurations are considered for studies. The results presented show that the proposed approach of fault location gives close to accurate results in terms of the estimated fault location

I. Introduction

THE power distribution system consists of a three-phase source supplying power through single-, two-, or three-phase distribution lines, switches, and transformers to a set of buses with a given load demand. In addition, unlike transmission systems, single-, two-, and three-phase sections exist in the network and single-, two-, and three-phase loads exist in the distribution networks. Further most distribution systems are overhead systems, which are susceptible to faults caused by a variety of situations such as adverse weather conditions, equipment failure, traffic accidents, etc. When a fault occurs on a distribution line, it is very important for the utility to identify the fault location as quickly as possible for improving the service reliability. A fault location in the distribution system (DS) is not an easy job due to its high complexity and difficulty caused by nonhomogeneity of line, fault resistance, load uncertainty, phase unbalance, long feeders with laterals and different network configurations under various load conditions [1]. Hence, one of the crucial blocks in the operation of such a DS is that of fault detection and it's location. This objective is achieved and depends on the success of the Distribution Automation (DA) System. The DA system should be implemented quickly and accurately in order to isolate those affected branches from the healthy parts and to take countermeasures to recover normal power supply.