Dynamic voltage collapse prediction in power systems using support vector regression

Muhammad Nizam, Azah Mohamed, Aini Hussain

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

This paper presents dynamic voltage collapse prediction on an actual power system using support vector regression. Dynamic voltage collapse prediction is first determined based on the PTSI calculated from information in dynamic simulation output. Simulations were carried out on a practical 87 bus test system by considering load increase as the contingency. The data collected from the time domain simulation is then used as input to the SVR in which support vector regression is used as a predictor to determine the dynamic voltage collapse indices of the power system. To reduce training time and improve accuracy of the SVR, the Kernel function type and Kernel parameter are considered. To verify the effectiveness of the proposed SVR method, its performance is compared with the multi layer perceptron neural network (MLPNN). Studies show that the SVM gives faster and more accurate results for dynamic voltage collapse prediction compared with the MLPNN.

Original languageEnglish
Pages (from-to)3730-3736
Number of pages7
JournalExpert Systems with Applications
Volume37
Issue number5
DOIs
Publication statusPublished - May 2010

Fingerprint

Electric potential
Multilayer neural networks
Neural networks
Computer simulation

Keywords

  • Artificial neural network
  • Dynamic voltage collapse
  • Prediction
  • Support vector machines

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Dynamic voltage collapse prediction in power systems using support vector regression. / Nizam, Muhammad; Mohamed, Azah; Hussain, Aini.

In: Expert Systems with Applications, Vol. 37, No. 5, 05.2010, p. 3730-3736.

Research output: Contribution to journalArticle

@article{cff5043e4df748efbccb2983f5c514a1,
title = "Dynamic voltage collapse prediction in power systems using support vector regression",
abstract = "This paper presents dynamic voltage collapse prediction on an actual power system using support vector regression. Dynamic voltage collapse prediction is first determined based on the PTSI calculated from information in dynamic simulation output. Simulations were carried out on a practical 87 bus test system by considering load increase as the contingency. The data collected from the time domain simulation is then used as input to the SVR in which support vector regression is used as a predictor to determine the dynamic voltage collapse indices of the power system. To reduce training time and improve accuracy of the SVR, the Kernel function type and Kernel parameter are considered. To verify the effectiveness of the proposed SVR method, its performance is compared with the multi layer perceptron neural network (MLPNN). Studies show that the SVM gives faster and more accurate results for dynamic voltage collapse prediction compared with the MLPNN.",
keywords = "Artificial neural network, Dynamic voltage collapse, Prediction, Support vector machines",
author = "Muhammad Nizam and Azah Mohamed and Aini Hussain",
year = "2010",
month = "5",
doi = "10.1016/j.eswa.2009.11.052",
language = "English",
volume = "37",
pages = "3730--3736",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Dynamic voltage collapse prediction in power systems using support vector regression

AU - Nizam, Muhammad

AU - Mohamed, Azah

AU - Hussain, Aini

PY - 2010/5

Y1 - 2010/5

N2 - This paper presents dynamic voltage collapse prediction on an actual power system using support vector regression. Dynamic voltage collapse prediction is first determined based on the PTSI calculated from information in dynamic simulation output. Simulations were carried out on a practical 87 bus test system by considering load increase as the contingency. The data collected from the time domain simulation is then used as input to the SVR in which support vector regression is used as a predictor to determine the dynamic voltage collapse indices of the power system. To reduce training time and improve accuracy of the SVR, the Kernel function type and Kernel parameter are considered. To verify the effectiveness of the proposed SVR method, its performance is compared with the multi layer perceptron neural network (MLPNN). Studies show that the SVM gives faster and more accurate results for dynamic voltage collapse prediction compared with the MLPNN.

AB - This paper presents dynamic voltage collapse prediction on an actual power system using support vector regression. Dynamic voltage collapse prediction is first determined based on the PTSI calculated from information in dynamic simulation output. Simulations were carried out on a practical 87 bus test system by considering load increase as the contingency. The data collected from the time domain simulation is then used as input to the SVR in which support vector regression is used as a predictor to determine the dynamic voltage collapse indices of the power system. To reduce training time and improve accuracy of the SVR, the Kernel function type and Kernel parameter are considered. To verify the effectiveness of the proposed SVR method, its performance is compared with the multi layer perceptron neural network (MLPNN). Studies show that the SVM gives faster and more accurate results for dynamic voltage collapse prediction compared with the MLPNN.

KW - Artificial neural network

KW - Dynamic voltage collapse

KW - Prediction

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=73249152434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73249152434&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2009.11.052

DO - 10.1016/j.eswa.2009.11.052

M3 - Article

VL - 37

SP - 3730

EP - 3736

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 5

ER -