ANN and Voltage-Drop Hybrid Method for Fault Location in Electrical Power Distribution Systems

Electric power distribution systems (EPDS) play a vital role in modern society. Efficient and precise restoration is crucial when distribution network faults arise to prevent customer claims and enhance service quality, leading to higher customer satisfaction. This cannot be achieved without an effective fault location method. This work proposes a new algorithm for locating the faulty section after single phase-to-ground faults (SPG). This algorithm uses the parameters of estimated fault distance and apparent reactance as inputs to an artificial neural network (ANN), trained to give the exact faulty section as a result. The testing of the technique is underway with numerical simulations using real data from an underground distribution feeder provided by the “Independent Agency for the Distribution of Water and Electricity and Liquid Cleansing of Kenitra” in Morocco. Comparative tests are intended to illustrate the precision and effectiveness of this approach.