This paper presents a new fault location method for an asymmetrical and unbalanced distribution feeder in the presence of distributed generations (DGs). In this study, a modified version of IEEE 34-bus test feeder with two fixed speed wind generators is considered. In the proposed method, at first, the type of short circuit is determined using the 3-phase current data that are measured at the substation. Then, to train and test the Artificial Neural Network (ANN), different operating patterns are produced for each type of short circuit. In order to cover the total operating space of the radial distribution network by ANNs; fault location, fault resistance, load of every node and power of DGs are changed in each pattern. For each type of short circuit, three different ANNs are used for estimation of the distance of fault to the substation and the interconnection of DGs. Inputs of the ANNs are 3-phase voltage and current which measured at the substation and the DG buses in pre fault and post fault stages. The results show low estimation error in testing of ANNs. For exact fault location, the estimated fault distance to the substation is compared with the estimated fault distance to the DG buses. Finally, the sensitivity of ANNs to the measuring error of the input data is examined.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.