New training strategies for RBF neural networks to determine fault location in a distribution network with DG units

Hadi Zayandehroodi, Azah Mohamed, Masoud Farhoodnea, Alireza Heidari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

This paper presents a new Radial Basis Function Neural Network with Optimum Steepest Descent (RBFNN-OSD) learning algorithm for identifying the exact faulty line section in the distribution network with high penetration level of Distributed Generation (DG) Units. In the proposed method, to determine the exact fault location, two RBFNN-OSD have been developed for various fault types. The first RBFNN-OSD is used for predicting the fault distance from the source and all DG units while the second RBFNN is used for identifying the exact faulty line. Several case studies have been simulated to verify the accuracy of the proposed method. Furthermore, the results of RBFNN-OSD and RBFNN with conventional steepest descent algorithm are also compared. The results show that the proposed RBFNN-OSD can accurately determine the location of faults in a test given distribution system with several DG units.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013
Pages450-454
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013 - Langkawi
Duration: 3 Jun 20134 Jun 2013

Other

Other2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013
CityLangkawi
Period3/6/134/6/13

Fingerprint

Electric fault location
Distributed power generation
Electric power distribution
Neural networks
Learning algorithms

Keywords

  • Distributed Generation (DG)
  • Fault Location
  • Optimum Steepest Descent Algorithm (OSD)
  • Radial Basis Function Neural Network (RBFNN)

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

Zayandehroodi, H., Mohamed, A., Farhoodnea, M., & Heidari, A. (2013). New training strategies for RBF neural networks to determine fault location in a distribution network with DG units. In Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013 (pp. 450-454). [6564590] https://doi.org/10.1109/PEOCO.2013.6564590

New training strategies for RBF neural networks to determine fault location in a distribution network with DG units. / Zayandehroodi, Hadi; Mohamed, Azah; Farhoodnea, Masoud; Heidari, Alireza.

Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013. 2013. p. 450-454 6564590.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zayandehroodi, H, Mohamed, A, Farhoodnea, M & Heidari, A 2013, New training strategies for RBF neural networks to determine fault location in a distribution network with DG units. in Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013., 6564590, pp. 450-454, 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013, Langkawi, 3/6/13. https://doi.org/10.1109/PEOCO.2013.6564590
Zayandehroodi H, Mohamed A, Farhoodnea M, Heidari A. New training strategies for RBF neural networks to determine fault location in a distribution network with DG units. In Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013. 2013. p. 450-454. 6564590 https://doi.org/10.1109/PEOCO.2013.6564590
Zayandehroodi, Hadi ; Mohamed, Azah ; Farhoodnea, Masoud ; Heidari, Alireza. / New training strategies for RBF neural networks to determine fault location in a distribution network with DG units. Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013. 2013. pp. 450-454
@inproceedings{b737f5ed8c764330ae7eb17d84daad5a,
title = "New training strategies for RBF neural networks to determine fault location in a distribution network with DG units",
abstract = "This paper presents a new Radial Basis Function Neural Network with Optimum Steepest Descent (RBFNN-OSD) learning algorithm for identifying the exact faulty line section in the distribution network with high penetration level of Distributed Generation (DG) Units. In the proposed method, to determine the exact fault location, two RBFNN-OSD have been developed for various fault types. The first RBFNN-OSD is used for predicting the fault distance from the source and all DG units while the second RBFNN is used for identifying the exact faulty line. Several case studies have been simulated to verify the accuracy of the proposed method. Furthermore, the results of RBFNN-OSD and RBFNN with conventional steepest descent algorithm are also compared. The results show that the proposed RBFNN-OSD can accurately determine the location of faults in a test given distribution system with several DG units.",
keywords = "Distributed Generation (DG), Fault Location, Optimum Steepest Descent Algorithm (OSD), Radial Basis Function Neural Network (RBFNN)",
author = "Hadi Zayandehroodi and Azah Mohamed and Masoud Farhoodnea and Alireza Heidari",
year = "2013",
doi = "10.1109/PEOCO.2013.6564590",
language = "English",
isbn = "9781467350730",
pages = "450--454",
booktitle = "Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013",

}

TY - GEN

T1 - New training strategies for RBF neural networks to determine fault location in a distribution network with DG units

AU - Zayandehroodi, Hadi

AU - Mohamed, Azah

AU - Farhoodnea, Masoud

AU - Heidari, Alireza

PY - 2013

Y1 - 2013

N2 - This paper presents a new Radial Basis Function Neural Network with Optimum Steepest Descent (RBFNN-OSD) learning algorithm for identifying the exact faulty line section in the distribution network with high penetration level of Distributed Generation (DG) Units. In the proposed method, to determine the exact fault location, two RBFNN-OSD have been developed for various fault types. The first RBFNN-OSD is used for predicting the fault distance from the source and all DG units while the second RBFNN is used for identifying the exact faulty line. Several case studies have been simulated to verify the accuracy of the proposed method. Furthermore, the results of RBFNN-OSD and RBFNN with conventional steepest descent algorithm are also compared. The results show that the proposed RBFNN-OSD can accurately determine the location of faults in a test given distribution system with several DG units.

AB - This paper presents a new Radial Basis Function Neural Network with Optimum Steepest Descent (RBFNN-OSD) learning algorithm for identifying the exact faulty line section in the distribution network with high penetration level of Distributed Generation (DG) Units. In the proposed method, to determine the exact fault location, two RBFNN-OSD have been developed for various fault types. The first RBFNN-OSD is used for predicting the fault distance from the source and all DG units while the second RBFNN is used for identifying the exact faulty line. Several case studies have been simulated to verify the accuracy of the proposed method. Furthermore, the results of RBFNN-OSD and RBFNN with conventional steepest descent algorithm are also compared. The results show that the proposed RBFNN-OSD can accurately determine the location of faults in a test given distribution system with several DG units.

KW - Distributed Generation (DG)

KW - Fault Location

KW - Optimum Steepest Descent Algorithm (OSD)

KW - Radial Basis Function Neural Network (RBFNN)

UR - http://www.scopus.com/inward/record.url?scp=84882764459&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882764459&partnerID=8YFLogxK

U2 - 10.1109/PEOCO.2013.6564590

DO - 10.1109/PEOCO.2013.6564590

M3 - Conference contribution

SN - 9781467350730

SP - 450

EP - 454

BT - Proceedings of the 2013 IEEE 7th International Power Engineering and Optimization Conference, PEOCO 2013

ER -