TY - JOUR
T1 - Automated fault location in a power system with distributed generations using radial basis function neural networks
AU - Zayandehroodi, H.
AU - Mohamed, A.
AU - Shareef, H.
AU - Mohammadjafari, M.
N1 - Funding Information:
This research was funded by the U.S. Department of Health & Human Services, U.S. Department of Education and U.S. Department of Juvenile Justice, Initiative on Safe School and Healthy Students.
PY - 2010
Y1 - 2010
N2 - High penetration of Distributed Generation (DG) units will have unfavorable impacts on the traditional fault location methods because the distribution system is no longer radial in nature and is not supplied by a single main power source. This study presents an automated fault location method using Radial Basis Function Neural Network (RBFNN) for a distribution system with DG units. In the proposed method, the fault type is determined first by normalizing the fault currents of the main source. Then to determine the fault location, two RBFNNs have been developed for various fault types. The first RBFNN is used for detraining fault distance from each source and the second RBFNN is used for identifying the exact faulty line. Several case studies have been used to verify the accuracy of the method. Furthermore, the results of RBFNN and the conventional Multi Layer Perception Neural Network (MLPNN) are also compared. The results showed that the proposed method can accurately determine the location of faults in a distribution system with several DG units.
AB - High penetration of Distributed Generation (DG) units will have unfavorable impacts on the traditional fault location methods because the distribution system is no longer radial in nature and is not supplied by a single main power source. This study presents an automated fault location method using Radial Basis Function Neural Network (RBFNN) for a distribution system with DG units. In the proposed method, the fault type is determined first by normalizing the fault currents of the main source. Then to determine the fault location, two RBFNNs have been developed for various fault types. The first RBFNN is used for detraining fault distance from each source and the second RBFNN is used for identifying the exact faulty line. Several case studies have been used to verify the accuracy of the method. Furthermore, the results of RBFNN and the conventional Multi Layer Perception Neural Network (MLPNN) are also compared. The results showed that the proposed method can accurately determine the location of faults in a distribution system with several DG units.
KW - Distributed generation (DG)
KW - Fault location
KW - Perception neural network (MLPNN)
KW - Power system
KW - Radial basis function neural network (RBFNN)
UR - http://www.scopus.com/inward/record.url?scp=78049400962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78049400962&partnerID=8YFLogxK
U2 - 10.3923/jas.2010.3032.3041
DO - 10.3923/jas.2010.3032.3041
M3 - Article
AN - SCOPUS:78049400962
SN - 1812-5654
VL - 10
SP - 3032
EP - 3041
JO - Journal of Applied Sciences
JF - Journal of Applied Sciences
IS - 23
ER -