Fault location in distribution networks using fuzzy clustering techniques

Abstract

This paper examines the problem of locating faults that may occur anywhere in electrical distribution networks and develops a solution using fuzzy c-mean clustering technique. In addition, it introduces methods for normalizing available data and selecting the optimum number of clusters for data classification. The developed technique is applied to an existing 13.8 kilovolt distribution network, which Serves an oil production field spread over an area of approximately sixty kilometers square. Simulation results have shown the feasibility and the effectiveness of the suggested fault location method.