INFLUENCE OF THE VARIATION IN THE LOAD AND THE SIZE OF THE ZONE IN THE ACCURACY OF A FAULT LOCATOR FOR DISTRIBUTION CIRCLE

A recent and interesting study topic to utilities engineers and customers has been the electric power quality. The product itself and the customer support are the main aspects considered. The product quality means satisIY requirements of wave quality and service continuity. Tbis last aspect is the one considered when the fault location problem is taken into account. This paper shows an analysis of a fault location method applied to power distribution systems, developed wilh a classifier based in support vectors machines. This fault lacator is trained using fault data from nominal conditions and tested considering lhe infiuence of load variations. Also its capability to maintain high performance indexes where the power system is sub-divided in a increasing number of zones is checked. From an application example which uses a model taken from a real power system, it is shown how lhe proposed approach is highly effective to salve the problem, having mean precision scores above 90% to locate the faulted zone, in case of single phase faults to ground, which is the most difficult case proposed.