Identification of stable and unstable power swings using pattern recognition

Pallav Kumar Bera, Can Isik

Research output: Chapter in Book/Entry/PoemConference contribution

5 Scopus citations

Abstract

Faults during symmetrical power swings cause maloperation of distance relay. Undesired operation also occurs during unstable power swings causing uncontrolled islanding. Faster detection of faults during power swings and classification of power swings can assist the protection system in making reliable decisions on blocking or unblocking a relay's operation. This paper segregates the faults, faults during power swing from power swings in one-cycle with an accuracy of 99.3%. It then identifies the different power swings in 10 cycles that occur in a 9-bus WSCC power system. Support Vector Machines (SVM), Decision Tree (DT), and k-Nearest Neighbor (kNN) classifiers are trained and tested on six features obtained from 3-phase(ph) relay voltage and current to test the validity of the detection and classification scheme. The different faults, faults during swings, and power swings are simulated in PSCAD/EMTDC.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 13th Annual IEEE Green Technologies Conference, GREENTECH 2021
PublisherIEEE Computer Society
Pages286-291
Number of pages6
ISBN (Electronic)9781728191393
DOIs
StatePublished - Apr 2021
Event13th Annual IEEE Green Technologies Conference, GREENTECH 2021 - Denver, United States
Duration: Apr 7 2021Apr 9 2021

Publication series

NameIEEE Green Technologies Conference
Volume2021-April
ISSN (Electronic)2166-5478

Conference

Conference13th Annual IEEE Green Technologies Conference, GREENTECH 2021
Country/TerritoryUnited States
CityDenver
Period4/7/214/9/21

Keywords

  • DT
  • Distance Protection
  • KNN
  • SVM
  • Stable Unstable Power Swings
  • Symmetrical Asymmetrical Swings

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Ecological Modeling
  • Environmental Engineering

Fingerprint

Dive into the research topics of 'Identification of stable and unstable power swings using pattern recognition'. Together they form a unique fingerprint.

Cite this