Using support vector machines for determining voltage unstable areas in power systems

Muhammad Nizam, Azah Mohamed, Majid Al-Dabbagh, Aini Hussain

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

5 Citations (Scopus)

Abstract

This paper presents the application of support vector machines (SVM) for determining voltage unstable areas in an actual power system. The voltage unstable area is first determined based on the power transfer stability index (PTSI) calculated using information obtained from 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 time domain simulations are then used as inputs to the SVM which acts as a classifier to determine the voltage unstable areas in the power system. To reduce training time and improve accuracy of the SVM, the Kernel function type and Kernel parameters are considered. To verify the effectiveness of the proposed SVM method, its performance is compared with the learning vector quantization (LVQ) technique. Studies show that the SVM gives similar classification accuracy as the LVQ with 100% accuracy. In terms of computational time, the SVM is faster than the LVQ.

Original languageEnglish
Title of host publicationPECon 2008 - 2008 IEEE 2nd International Power and Energy Conference
Pages878-883
Number of pages6
DOIs
Publication statusPublished - 2008
Event2008 IEEE 2nd International Power and Energy Conference, PECon 2008 - Johor Baharu
Duration: 1 Dec 20083 Dec 2008

Other

Other2008 IEEE 2nd International Power and Energy Conference, PECon 2008
CityJohor Baharu
Period1/12/083/12/08

Fingerprint

Support vector machines
Vector quantization
Electric potential
Classifiers
Computer simulation

Keywords

  • Learning Vector Quantization
  • Support vector machine
  • Voltage unstable area

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Nizam, M., Mohamed, A., Al-Dabbagh, M., & Hussain, A. (2008). Using support vector machines for determining voltage unstable areas in power systems. In PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference (pp. 878-883). [4762599] https://doi.org/10.1109/PECON.2008.4762599

Using support vector machines for determining voltage unstable areas in power systems. / Nizam, Muhammad; Mohamed, Azah; Al-Dabbagh, Majid; Hussain, Aini.

PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. p. 878-883 4762599.

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

Nizam, M, Mohamed, A, Al-Dabbagh, M & Hussain, A 2008, Using support vector machines for determining voltage unstable areas in power systems. in PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference., 4762599, pp. 878-883, 2008 IEEE 2nd International Power and Energy Conference, PECon 2008, Johor Baharu, 1/12/08. https://doi.org/10.1109/PECON.2008.4762599
Nizam M, Mohamed A, Al-Dabbagh M, Hussain A. Using support vector machines for determining voltage unstable areas in power systems. In PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. p. 878-883. 4762599 https://doi.org/10.1109/PECON.2008.4762599
Nizam, Muhammad ; Mohamed, Azah ; Al-Dabbagh, Majid ; Hussain, Aini. / Using support vector machines for determining voltage unstable areas in power systems. PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. pp. 878-883
@inproceedings{7ad9a9942aa1408988ab19929bebda58,
title = "Using support vector machines for determining voltage unstable areas in power systems",
abstract = "This paper presents the application of support vector machines (SVM) for determining voltage unstable areas in an actual power system. The voltage unstable area is first determined based on the power transfer stability index (PTSI) calculated using information obtained from 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 time domain simulations are then used as inputs to the SVM which acts as a classifier to determine the voltage unstable areas in the power system. To reduce training time and improve accuracy of the SVM, the Kernel function type and Kernel parameters are considered. To verify the effectiveness of the proposed SVM method, its performance is compared with the learning vector quantization (LVQ) technique. Studies show that the SVM gives similar classification accuracy as the LVQ with 100{\%} accuracy. In terms of computational time, the SVM is faster than the LVQ.",
keywords = "Learning Vector Quantization, Support vector machine, Voltage unstable area",
author = "Muhammad Nizam and Azah Mohamed and Majid Al-Dabbagh and Aini Hussain",
year = "2008",
doi = "10.1109/PECON.2008.4762599",
language = "English",
isbn = "9781424424054",
pages = "878--883",
booktitle = "PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference",

}

TY - GEN

T1 - Using support vector machines for determining voltage unstable areas in power systems

AU - Nizam, Muhammad

AU - Mohamed, Azah

AU - Al-Dabbagh, Majid

AU - Hussain, Aini

PY - 2008

Y1 - 2008

N2 - This paper presents the application of support vector machines (SVM) for determining voltage unstable areas in an actual power system. The voltage unstable area is first determined based on the power transfer stability index (PTSI) calculated using information obtained from 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 time domain simulations are then used as inputs to the SVM which acts as a classifier to determine the voltage unstable areas in the power system. To reduce training time and improve accuracy of the SVM, the Kernel function type and Kernel parameters are considered. To verify the effectiveness of the proposed SVM method, its performance is compared with the learning vector quantization (LVQ) technique. Studies show that the SVM gives similar classification accuracy as the LVQ with 100% accuracy. In terms of computational time, the SVM is faster than the LVQ.

AB - This paper presents the application of support vector machines (SVM) for determining voltage unstable areas in an actual power system. The voltage unstable area is first determined based on the power transfer stability index (PTSI) calculated using information obtained from 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 time domain simulations are then used as inputs to the SVM which acts as a classifier to determine the voltage unstable areas in the power system. To reduce training time and improve accuracy of the SVM, the Kernel function type and Kernel parameters are considered. To verify the effectiveness of the proposed SVM method, its performance is compared with the learning vector quantization (LVQ) technique. Studies show that the SVM gives similar classification accuracy as the LVQ with 100% accuracy. In terms of computational time, the SVM is faster than the LVQ.

KW - Learning Vector Quantization

KW - Support vector machine

KW - Voltage unstable area

UR - http://www.scopus.com/inward/record.url?scp=63049136600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63049136600&partnerID=8YFLogxK

U2 - 10.1109/PECON.2008.4762599

DO - 10.1109/PECON.2008.4762599

M3 - Conference contribution

AN - SCOPUS:63049136600

SN - 9781424424054

SP - 878

EP - 883

BT - PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference

ER -