A new method of transient stability assessment in power systems using LS-SVM

A. W Noor Izzri, Azah Mohamed, Iskandar Yahya

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

8 Citations (Scopus)

Abstract

This paper presents transient stability assessment of electrical power system using least squares support vector machine (LS-SVM) and principle component analysis. Transient stability of a power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the IEEE 9-bus test system considering three phase faults on the system. The data collected from the time domain simulations are then used as inputs to the LS-SVM in which LS-SVM is used as a classifier to determine the stability state of a power system. Principle component analysis is applied to extract useful input features to the LS-SVM so that training time of the LS-SVM can be reduced. To verify the effectiveness of the proposed LS-SVM method, its performance is compared with the multi layer perceptron neural network. Results show that the LS-SVM gives faster and more accurate transient stability assessment compared to the multi layer perceptron neural network in terms of classification results.

Original languageEnglish
Title of host publication2007 5th Student Conference on Research and Development, SCORED
DOIs
Publication statusPublished - 2007
Event2007 5th Student Conference on Research and Development, SCORED - Selangor
Duration: 11 Dec 200712 Dec 2007

Other

Other2007 5th Student Conference on Research and Development, SCORED
CitySelangor
Period11/12/0712/12/07

Fingerprint

neural network
simulation
Power system
Least squares support vector machine
performance
time
Simulation
Neural networks
Bus
Generator
Classifier
Fault

Keywords

  • And least squares support vector machines
  • Artificial neural network
  • Dynamic Security Assessment
  • Time domain simulation method
  • Transient stability assessment

ASJC Scopus subject areas

  • Education
  • Management Science and Operations Research

Cite this

Izzri, A. W. N., Mohamed, A., & Yahya, I. (2007). A new method of transient stability assessment in power systems using LS-SVM. In 2007 5th Student Conference on Research and Development, SCORED [4451446] https://doi.org/10.1109/SCORED.2007.4451446

A new method of transient stability assessment in power systems using LS-SVM. / Izzri, A. W Noor; Mohamed, Azah; Yahya, Iskandar.

2007 5th Student Conference on Research and Development, SCORED. 2007. 4451446.

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

Izzri, AWN, Mohamed, A & Yahya, I 2007, A new method of transient stability assessment in power systems using LS-SVM. in 2007 5th Student Conference on Research and Development, SCORED., 4451446, 2007 5th Student Conference on Research and Development, SCORED, Selangor, 11/12/07. https://doi.org/10.1109/SCORED.2007.4451446
Izzri AWN, Mohamed A, Yahya I. A new method of transient stability assessment in power systems using LS-SVM. In 2007 5th Student Conference on Research and Development, SCORED. 2007. 4451446 https://doi.org/10.1109/SCORED.2007.4451446
Izzri, A. W Noor ; Mohamed, Azah ; Yahya, Iskandar. / A new method of transient stability assessment in power systems using LS-SVM. 2007 5th Student Conference on Research and Development, SCORED. 2007.
@inproceedings{fc9b69dd5d694e2698b7aaa911f2b02f,
title = "A new method of transient stability assessment in power systems using LS-SVM",
abstract = "This paper presents transient stability assessment of electrical power system using least squares support vector machine (LS-SVM) and principle component analysis. Transient stability of a power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the IEEE 9-bus test system considering three phase faults on the system. The data collected from the time domain simulations are then used as inputs to the LS-SVM in which LS-SVM is used as a classifier to determine the stability state of a power system. Principle component analysis is applied to extract useful input features to the LS-SVM so that training time of the LS-SVM can be reduced. To verify the effectiveness of the proposed LS-SVM method, its performance is compared with the multi layer perceptron neural network. Results show that the LS-SVM gives faster and more accurate transient stability assessment compared to the multi layer perceptron neural network in terms of classification results.",
keywords = "And least squares support vector machines, Artificial neural network, Dynamic Security Assessment, Time domain simulation method, Transient stability assessment",
author = "Izzri, {A. W Noor} and Azah Mohamed and Iskandar Yahya",
year = "2007",
doi = "10.1109/SCORED.2007.4451446",
language = "English",
isbn = "1424414709",
booktitle = "2007 5th Student Conference on Research and Development, SCORED",

}

TY - GEN

T1 - A new method of transient stability assessment in power systems using LS-SVM

AU - Izzri, A. W Noor

AU - Mohamed, Azah

AU - Yahya, Iskandar

PY - 2007

Y1 - 2007

N2 - This paper presents transient stability assessment of electrical power system using least squares support vector machine (LS-SVM) and principle component analysis. Transient stability of a power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the IEEE 9-bus test system considering three phase faults on the system. The data collected from the time domain simulations are then used as inputs to the LS-SVM in which LS-SVM is used as a classifier to determine the stability state of a power system. Principle component analysis is applied to extract useful input features to the LS-SVM so that training time of the LS-SVM can be reduced. To verify the effectiveness of the proposed LS-SVM method, its performance is compared with the multi layer perceptron neural network. Results show that the LS-SVM gives faster and more accurate transient stability assessment compared to the multi layer perceptron neural network in terms of classification results.

AB - This paper presents transient stability assessment of electrical power system using least squares support vector machine (LS-SVM) and principle component analysis. Transient stability of a power system is first determined based on the generator relative rotor angles obtained from time domain simulation outputs. Simulations were carried out on the IEEE 9-bus test system considering three phase faults on the system. The data collected from the time domain simulations are then used as inputs to the LS-SVM in which LS-SVM is used as a classifier to determine the stability state of a power system. Principle component analysis is applied to extract useful input features to the LS-SVM so that training time of the LS-SVM can be reduced. To verify the effectiveness of the proposed LS-SVM method, its performance is compared with the multi layer perceptron neural network. Results show that the LS-SVM gives faster and more accurate transient stability assessment compared to the multi layer perceptron neural network in terms of classification results.

KW - And least squares support vector machines

KW - Artificial neural network

KW - Dynamic Security Assessment

KW - Time domain simulation method

KW - Transient stability assessment

UR - http://www.scopus.com/inward/record.url?scp=50449104656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50449104656&partnerID=8YFLogxK

U2 - 10.1109/SCORED.2007.4451446

DO - 10.1109/SCORED.2007.4451446

M3 - Conference contribution

AN - SCOPUS:50449104656

SN - 1424414709

SN - 9781424414703

BT - 2007 5th Student Conference on Research and Development, SCORED

ER -