Risk based security assessment of power system using generalized regression neural network with feature extraction

M. Marsadek, Azah Mohamed

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.

Original languageEnglish
Pages (from-to)466-479
Number of pages14
JournalJournal of Central South University
Volume20
Issue number2
DOIs
Publication statusPublished - Feb 2013

Fingerprint

Feature extraction
Neural networks
Electric potential
Outages
Principal component analysis
Screening

Keywords

  • generalized regression neural network
  • line overload
  • low voltage
  • principle component analysis
  • risk index
  • voltage collapse

ASJC Scopus subject areas

  • Engineering(all)
  • Metals and Alloys

Cite this

Risk based security assessment of power system using generalized regression neural network with feature extraction. / Marsadek, M.; Mohamed, Azah.

In: Journal of Central South University, Vol. 20, No. 2, 02.2013, p. 466-479.

Research output: Contribution to journalArticle

@article{f30d4c99c0ff431f89563aa6df18ec7e,
title = "Risk based security assessment of power system using generalized regression neural network with feature extraction",
abstract = "A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.",
keywords = "generalized regression neural network, line overload, low voltage, principle component analysis, risk index, voltage collapse",
author = "M. Marsadek and Azah Mohamed",
year = "2013",
month = "2",
doi = "10.1007/s11771-013-1508-9",
language = "English",
volume = "20",
pages = "466--479",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "Springer Science + Business Media",
number = "2",

}

TY - JOUR

T1 - Risk based security assessment of power system using generalized regression neural network with feature extraction

AU - Marsadek, M.

AU - Mohamed, Azah

PY - 2013/2

Y1 - 2013/2

N2 - A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.

AB - A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.

KW - generalized regression neural network

KW - line overload

KW - low voltage

KW - principle component analysis

KW - risk index

KW - voltage collapse

UR - http://www.scopus.com/inward/record.url?scp=84890537980&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890537980&partnerID=8YFLogxK

U2 - 10.1007/s11771-013-1508-9

DO - 10.1007/s11771-013-1508-9

M3 - Article

AN - SCOPUS:84890537980

VL - 20

SP - 466

EP - 479

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 2

ER -