Header menu link for other important links
Fault identification and location in distribution systems using support vector machines
K.S. Kumar, , S. Naveen
Published in EuroJournals, Inc.
Volume: 51
Issue: 1
Pages: 53 - 60
This paper investigates the capability of SVM for prediction of fault in power system. The SVM, as a novel type of machine learning based on statistical learning theory, achieves good generalization ability by adopting a structural risk minimization (SRM) induction principle that aims at minimizing a bound on the generalization error of a model rather than the minimizing the error on the training data only. Here, SVM has been used as a classification. The inputs of SVM model are Power and Voltage Values. A comparative study gas been done between the developed SVM model and LVQ ANN model. An equation has been developed for the prediction of fault in power system based on the developed SVM model. This study shows that the developed SVM model can be used as practical tool for prediction of faults in other systems too apart from the test case. © EuroJournals Publishing, Inc. 2011.
About the journal
JournalEuropean Journal of Scientific Research
PublisherEuroJournals, Inc.