Islanding detection for multi DG system using inverter based DGs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

in this paper a multiple distributed-generation (DG) system was used to test the proposed islanding detection technique for grid-mode distributed-generation (DG). Twenty one features are extracted from measurement of the voltage and frequency at the point of common coupling (PCC) in order to identify islanding occurrence with high accuracy. An IEEE 34-bus system was used in this paper to generate islanding and non-islanding cases. Multiple locations for the DGs were used and also multiple DGs were also connected. Naïve Bayes Classifier then was used to discriminate between islanding and non-islanding. In order to test the accuracy of the Naïve Bayesian Classifier, Cross-Validation was used to evaluate the performance of the proposed islanding detection technique. Also, the algorithm was tested against Support Vector Machine (SVM). The results show the superiority of the Naïve Bayes Classifier over the SVM.

Original languageBritish English
Title of host publication2013 IEEE Power and Energy Society General Meeting, PES 2013
DOIs
StatePublished - 2013
Event2013 IEEE Power and Energy Society General Meeting, PES 2013 - Vancouver, BC, Canada
Duration: 21 Jul 201325 Jul 2013

Publication series

NameIEEE Power and Energy Society General Meeting
ISSN (Print)1944-9925
ISSN (Electronic)1944-9933

Conference

Conference2013 IEEE Power and Energy Society General Meeting, PES 2013
Country/TerritoryCanada
CityVancouver, BC
Period21/07/1325/07/13

Keywords

  • Cross Validation
  • inverter-based distributed generator
  • islanding detection
  • Naïve Bayes
  • power systems
  • Support Vector Machine
  • WEKA

Fingerprint

Dive into the research topics of 'Islanding detection for multi DG system using inverter based DGs'. Together they form a unique fingerprint.

Cite this