Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs

Hadi Zayandehroodi, Azah Mohamed, Hussain Shareef, Marjan Mohammadjafari

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

15 Citations (Scopus)

Abstract

With high penetration of distributed generations (DGs), power distribution system is regarded as a multisource system in which fault location scheme must be direction sensitive. This paper 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 first determined by normalizing the fault currents of the main source and then fault location is predicted by using RBFNN. Several case studies have been considered to verify the accuracy of the RBFNN. A comparison is also made between the RBFNN and the conventional multilayer perceptron neural network for locating faults in a power distribution system with DGs. The test results showed that the RBFNN can accurately determine the location of faults in a distribution system with several DG units.

Original languageEnglish
Title of host publicationPECon2010 - 2010 IEEE International Conference on Power and Energy
Pages341-345
Number of pages5
DOIs
Publication statusPublished - 2010
Event2010 IEEE International Conference on Power and Energy, PECon2010 - Kuala Lumpur
Duration: 29 Nov 20101 Dec 2010

Other

Other2010 IEEE International Conference on Power and Energy, PECon2010
CityKuala Lumpur
Period29/11/101/12/10

Fingerprint

Electric fault location
Distributed power generation
Electric power distribution
Neural networks
Electric fault currents
Multilayer neural networks

Keywords

  • Distributed generation (DG)
  • Distribution network
  • Fault location
  • Multilayer perceptron neural network (MLPNN)
  • Radial basis function neural network (RBFNN)

ASJC Scopus subject areas

  • Energy Engineering and Power Technology

Cite this

Zayandehroodi, H., Mohamed, A., Shareef, H., & Mohammadjafari, M. (2010). Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs. In PECon2010 - 2010 IEEE International Conference on Power and Energy (pp. 341-345). [5699422] https://doi.org/10.1109/PECON.2010.5699422

Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs. / Zayandehroodi, Hadi; Mohamed, Azah; Shareef, Hussain; Mohammadjafari, Marjan.

PECon2010 - 2010 IEEE International Conference on Power and Energy. 2010. p. 341-345 5699422.

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

Zayandehroodi, H, Mohamed, A, Shareef, H & Mohammadjafari, M 2010, Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs. in PECon2010 - 2010 IEEE International Conference on Power and Energy., 5699422, pp. 341-345, 2010 IEEE International Conference on Power and Energy, PECon2010, Kuala Lumpur, 29/11/10. https://doi.org/10.1109/PECON.2010.5699422
Zayandehroodi H, Mohamed A, Shareef H, Mohammadjafari M. Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs. In PECon2010 - 2010 IEEE International Conference on Power and Energy. 2010. p. 341-345. 5699422 https://doi.org/10.1109/PECON.2010.5699422
Zayandehroodi, Hadi ; Mohamed, Azah ; Shareef, Hussain ; Mohammadjafari, Marjan. / Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs. PECon2010 - 2010 IEEE International Conference on Power and Energy. 2010. pp. 341-345
@inproceedings{7e166336e09a40bcaf8925214fab77de,
title = "Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs",
abstract = "With high penetration of distributed generations (DGs), power distribution system is regarded as a multisource system in which fault location scheme must be direction sensitive. This paper 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 first determined by normalizing the fault currents of the main source and then fault location is predicted by using RBFNN. Several case studies have been considered to verify the accuracy of the RBFNN. A comparison is also made between the RBFNN and the conventional multilayer perceptron neural network for locating faults in a power distribution system with DGs. The test results showed that the RBFNN can accurately determine the location of faults in a distribution system with several DG units.",
keywords = "Distributed generation (DG), Distribution network, Fault location, Multilayer perceptron neural network (MLPNN), Radial basis function neural network (RBFNN)",
author = "Hadi Zayandehroodi and Azah Mohamed and Hussain Shareef and Marjan Mohammadjafari",
year = "2010",
doi = "10.1109/PECON.2010.5699422",
language = "English",
isbn = "9781424489466",
pages = "341--345",
booktitle = "PECon2010 - 2010 IEEE International Conference on Power and Energy",

}

TY - GEN

T1 - Performance comparison of mlp and rbf neural networks for fault location in distribution networks with DGs

AU - Zayandehroodi, Hadi

AU - Mohamed, Azah

AU - Shareef, Hussain

AU - Mohammadjafari, Marjan

PY - 2010

Y1 - 2010

N2 - With high penetration of distributed generations (DGs), power distribution system is regarded as a multisource system in which fault location scheme must be direction sensitive. This paper 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 first determined by normalizing the fault currents of the main source and then fault location is predicted by using RBFNN. Several case studies have been considered to verify the accuracy of the RBFNN. A comparison is also made between the RBFNN and the conventional multilayer perceptron neural network for locating faults in a power distribution system with DGs. The test results showed that the RBFNN can accurately determine the location of faults in a distribution system with several DG units.

AB - With high penetration of distributed generations (DGs), power distribution system is regarded as a multisource system in which fault location scheme must be direction sensitive. This paper 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 first determined by normalizing the fault currents of the main source and then fault location is predicted by using RBFNN. Several case studies have been considered to verify the accuracy of the RBFNN. A comparison is also made between the RBFNN and the conventional multilayer perceptron neural network for locating faults in a power distribution system with DGs. The test results showed that the RBFNN can accurately determine the location of faults in a distribution system with several DG units.

KW - Distributed generation (DG)

KW - Distribution network

KW - Fault location

KW - Multilayer perceptron neural network (MLPNN)

KW - Radial basis function neural network (RBFNN)

UR - http://www.scopus.com/inward/record.url?scp=79951801980&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951801980&partnerID=8YFLogxK

U2 - 10.1109/PECON.2010.5699422

DO - 10.1109/PECON.2010.5699422

M3 - Conference contribution

SN - 9781424489466

SP - 341

EP - 345

BT - PECon2010 - 2010 IEEE International Conference on Power and Energy

ER -