Volume 13 Number 4 (Apr. 2018)
Home > Archive > 2018 > Volume 13 Number 4 (Apr. 2018) >
JCP 2018 Vol.13(4): 417-425 ISSN: 1796-203X
doi: 10.17706/jcp.13.4.417-425

Hybrid GSA-ANN Methods to Forecast Sheath Current of High Voltage Underground Cable Lines

Bahadır Akbal
Selçuk University, Engineering Faculty, Department of Electrical and Electronics Engineering Konya, Turkey.

Abstract—Electrical safety is major issue for electric networks, so high voltage underground cable lines have been used instead of overhead line recently in city center and neighborhood. However, sheath current generates on metallic sheath of high voltage underground cable, and sheath current causes major cable faults and electroshock. Single point bonding, solid bonding and cross bonding are used to reduce sheath current and voltage. If sheath current is determined before high voltage underground cable line is installed, the most suitable method can be used to reduce sheath current and voltage. Hence, cable faults and electroshock can be prevented. There are many factors in formation of sheath current. Thus, formulation of sheath current is very complex and difficult. In this case forecasting methods can be used to determine sheath current, and artificial neural network (ANN) is a powerful method for forecasting studies. In this study, Gravitational Search Algorithm (GSA) and artificial neural network (ANN) is used to reduce training error, and hybrid GSA-ANN method is obtained. It is seen at the end of this study that errors of hybrid GSA-ANN method are less than errors of classic ANN.

Index Terms—Artificial neural network, GSA, sheath current, high voltage underground cable line.

[PDF]

Cite:Bahadır Akbal, "Hybrid GSA-ANN Methods to Forecast Sheath Current of High Voltage Underground Cable Lines," Journal of Computers vol. 13, no. 4, pp. 417-425, 2018.

General Information

ISSN: 1796-203X
Frequency: Monthly (2006-2014); Bimonthly (Since 2015)
Editor-in-Chief: Prof. Liansheng Tan
Executive Editor: Ms. Cherry L. Chen
Abstracting/ Indexing: DBLP, EBSCO, DOAJ, ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat, CNKI,etc
E-mail: jcp@iap.org
  • Aug 14, 2017 News!

    Vol 13, No 5 has been published with online version   [Click]

  • Jun 21, 2017 News!

    Vol 13, No 4 has been published with online version   [Click]

  • Jun 14, 2017 News!

    Vol 13, No 3 has been published with online version   [Click]

  • May 24, 2017 News!

    Vol 13, No 2 has been published with online version   [Click]

  • May 24, 2017 News!

    Vol 13, No 1 has been published with online version   [Click]

  • Read more>>