Classification and regression analysis using support vector machine for classifying and locating faults in a distribution system

Abstract

Various fault location methods have been developed in the past to identify the faulty phase, fault type,faulty section, and distance. However, this identification is commonly conducted in a separate manner. An effectivefault location should be able to identify all of these at the same time. Therefore, in this work, a method using a supportvector machine (SVM) to identify the fault type, faulty section, and distance considering the faulty phase is proposed.The proposed method uses voltage sag magnitude of the distribution system as the main feature for the SVM to identifyfaults. The fault type is classified using a directed acyclic graph SVM. The possible faulty sections are identified byestimating the fault resistance using support vector regression and matching the voltage sag data in the database withthe actual voltage sag data. The most possible faulty sections are ranked using ranking analysis. The fault distance forthe possible faulty sections is then identified using support vector regression analysis and its overfitting or underfittingissues are addressed by the proper selection of a regularization parameter. The feasibility of the proposed method wastested on an actual Malaysian distribution system. The results of faulty phase, fault type, faulty section, and faultdistance are analyzed. The performance of the proposed method is compared with various other intelligent methods suchas the artificial neural network, deep neural network, extreme learning machine, and kriging method. The test resultsindicate that the faulty phase and fault type yield 100% accurate results. All the faulty sections are identified and theproposed method obtains reliable fault location.