Reactive power allocation using support vector machine

M. W. Mustafa, S. N. Khalid, A. Khairuddin, H. Shareef

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

Abstract

This paper proposes a new modified nodal equations (MNE) method to identify the reactive power transfer between generators and load. It further focuses on creating an appropriate support vector machine (SVM) in which support vector regression is used as an estimator to solve the same problem in a simpler and faster manner. Almost all system variables obtained from load flow solutions are utilized as input to the SVM. The actual 25-bus equivalent power system of south Malaysia is utilized as a test system to illustrate the effectiveness of the SVM technique compared to that of the modified nodal equations method.

Original languageEnglish
Title of host publicationIMCIC 2010 - International Multi-Conference on Complexity, Informatics and Cybernetics, Proceedings
EditorsJorge Baralt, Michael J. Savoie, Hsing-Wei Chu, C. Dale Zinn, Nagib C. Callaos
PublisherInternational Institute of Informatics and Systemics, IIIS
Pages41-46
Number of pages6
ISBN (Electronic)9781934272916
Publication statusPublished - 2010
Externally publishedYes
EventInternational Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2010 - Orlando, United States
Duration: Apr 6 2010Apr 9 2010

Publication series

NameIMCIC 2010 - International Multi-Conference on Complexity, Informatics and Cybernetics, Proceedings
Volume1

Conference

ConferenceInternational Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2010
Country/TerritoryUnited States
CityOrlando
Period4/6/104/9/10

Keywords

  • Load flow
  • Modified nodal equations method
  • Radial basis function network
  • Reactive power and support vector machine

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Reactive power allocation using support vector machine'. Together they form a unique fingerprint.

Cite this