Sensitivity analysis of a single phase fault locator based on support vector machines

This paper presents a sensitivity analysis of a fault locator, for power distribution systems, aimed to determine those parameters that have the greatest influence on the location performance. The sampling process for sensitivity analysis is performed with an optimal Tabu based Latin hypercube method, and it was combined with the regression analysis to determine the influence of each parameter on the fault locator. The proposed methodology is tested in a standard IEEE 34-bus power distribution system, which is subdivided into 12 zones, considering a database of 66420 different fault conditions. Sensitivity analysis shows that standarization method is the one that has the greatest influence on the fault locator performance.