A support vector machine (SVM) based voltage stability classifier

Rodel D. Dosano, Hwachang Song, Byong Jun Lee

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

Abstract

This paper proposes a support vector machine (SVM) based power system voltage stability classifier using local measurements of voltage and active power of load. The excellent performance of the SVM in the classification related to time-series prediction matches the real-time data of local measurement for system responses by shortterm and long-term dynamics. The methodology for automatic monitoring of the system is initiated locally, which aims to leave sufficient time to perform immediate corrective actions to stop system degradation by the effect of major disturbances. This paper explains the procedure for fast classification of long-term voltage stability using the SVM algorithm.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Energy and Power Systems
Pages265-271
Number of pages7
Publication statusPublished - 2007 Dec 1
Event7th IASTED International Conference on Power and Energy Systems - Palma de Mallorca, Spain
Duration: 2007 Aug 292007 Aug 31

Other

Other7th IASTED International Conference on Power and Energy Systems
CountrySpain
CityPalma de Mallorca
Period07/8/2907/8/31

Fingerprint

classifiers
Voltage control
Support vector machines
Classifiers
electric potential
Time series
disturbances
methodology
degradation
Degradation
Monitoring
Electric potential
predictions

Keywords

  • Classification
  • Local phasor measurement
  • Power system voltage stability
  • Real-time monitoring
  • Support vector machine

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Dosano, R. D., Song, H., & Lee, B. J. (2007). A support vector machine (SVM) based voltage stability classifier. In Proceedings of the IASTED International Conference on Energy and Power Systems (pp. 265-271)

A support vector machine (SVM) based voltage stability classifier. / Dosano, Rodel D.; Song, Hwachang; Lee, Byong Jun.

Proceedings of the IASTED International Conference on Energy and Power Systems. 2007. p. 265-271.

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

Dosano, RD, Song, H & Lee, BJ 2007, A support vector machine (SVM) based voltage stability classifier. in Proceedings of the IASTED International Conference on Energy and Power Systems. pp. 265-271, 7th IASTED International Conference on Power and Energy Systems, Palma de Mallorca, Spain, 07/8/29.
Dosano RD, Song H, Lee BJ. A support vector machine (SVM) based voltage stability classifier. In Proceedings of the IASTED International Conference on Energy and Power Systems. 2007. p. 265-271
Dosano, Rodel D. ; Song, Hwachang ; Lee, Byong Jun. / A support vector machine (SVM) based voltage stability classifier. Proceedings of the IASTED International Conference on Energy and Power Systems. 2007. pp. 265-271
@inproceedings{0f61ad4941174e05b3072f9fe8893f77,
title = "A support vector machine (SVM) based voltage stability classifier",
abstract = "This paper proposes a support vector machine (SVM) based power system voltage stability classifier using local measurements of voltage and active power of load. The excellent performance of the SVM in the classification related to time-series prediction matches the real-time data of local measurement for system responses by shortterm and long-term dynamics. The methodology for automatic monitoring of the system is initiated locally, which aims to leave sufficient time to perform immediate corrective actions to stop system degradation by the effect of major disturbances. This paper explains the procedure for fast classification of long-term voltage stability using the SVM algorithm.",
keywords = "Classification, Local phasor measurement, Power system voltage stability, Real-time monitoring, Support vector machine",
author = "Dosano, {Rodel D.} and Hwachang Song and Lee, {Byong Jun}",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9780889866898",
pages = "265--271",
booktitle = "Proceedings of the IASTED International Conference on Energy and Power Systems",

}

TY - GEN

T1 - A support vector machine (SVM) based voltage stability classifier

AU - Dosano, Rodel D.

AU - Song, Hwachang

AU - Lee, Byong Jun

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper proposes a support vector machine (SVM) based power system voltage stability classifier using local measurements of voltage and active power of load. The excellent performance of the SVM in the classification related to time-series prediction matches the real-time data of local measurement for system responses by shortterm and long-term dynamics. The methodology for automatic monitoring of the system is initiated locally, which aims to leave sufficient time to perform immediate corrective actions to stop system degradation by the effect of major disturbances. This paper explains the procedure for fast classification of long-term voltage stability using the SVM algorithm.

AB - This paper proposes a support vector machine (SVM) based power system voltage stability classifier using local measurements of voltage and active power of load. The excellent performance of the SVM in the classification related to time-series prediction matches the real-time data of local measurement for system responses by shortterm and long-term dynamics. The methodology for automatic monitoring of the system is initiated locally, which aims to leave sufficient time to perform immediate corrective actions to stop system degradation by the effect of major disturbances. This paper explains the procedure for fast classification of long-term voltage stability using the SVM algorithm.

KW - Classification

KW - Local phasor measurement

KW - Power system voltage stability

KW - Real-time monitoring

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=56149114746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149114746&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56149114746

SN - 9780889866898

SP - 265

EP - 271

BT - Proceedings of the IASTED International Conference on Energy and Power Systems

ER -