A neural network based ATC assessment incorporating novel feature selection and extraction methods

M. M. Othman, Azah Mohamed, Aini Hussain

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This article presents a neural network based method for assessing the inter-area available transfer capability (ATC) of power systems aimed at providing a fast and accurate ATC. In the neural network implementation, the Levenberg-Marquardt modified back propagation algorithm is used in the training of the neural network so as to improve the speed and the convergence in the training process. One of the important considerations in applying neural network to transfer capability assessment is the proper selection and extraction of neural network input features. To achieve this, a hybrid method consisting of both the sensitivity and discrete Fourier transform methods are used in which the sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform method for extracting the meaningful features. To illustrate the effectiveness of the proposed methods, ATC simulations have been performed on the Malaysian power system. Neural network results shows that better ATC assessment accuracy can be obtained by selecting and extracting features using the proposed methods as compared to using only the discrete Fourier transform or the sensitivity methods. Results have also shown that the method is capable of reflecting accurate variations in load levels and effect of contingencies such as line outages. Computational time can be greatly reduced by using the neural network based ATC assessment method and, therefore, it can be used to provide a real time market signal of the capability of a transmission system in delivering power.

Original languageEnglish
Pages (from-to)1121-1136
Number of pages16
JournalElectric Power Components and Systems
Volume32
Issue number11
DOIs
Publication statusPublished - Nov 2004

Fingerprint

Feature extraction
Neural networks
Discrete Fourier transforms
Backpropagation algorithms
Outages
Sensitivity analysis

Keywords

  • Neural network
  • Transfer capability
  • Transmission systems

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A neural network based ATC assessment incorporating novel feature selection and extraction methods. / Othman, M. M.; Mohamed, Azah; Hussain, Aini.

In: Electric Power Components and Systems, Vol. 32, No. 11, 11.2004, p. 1121-1136.

Research output: Contribution to journalArticle

@article{b7f771e50827433d92d53e2651dd6edd,
title = "A neural network based ATC assessment incorporating novel feature selection and extraction methods",
abstract = "This article presents a neural network based method for assessing the inter-area available transfer capability (ATC) of power systems aimed at providing a fast and accurate ATC. In the neural network implementation, the Levenberg-Marquardt modified back propagation algorithm is used in the training of the neural network so as to improve the speed and the convergence in the training process. One of the important considerations in applying neural network to transfer capability assessment is the proper selection and extraction of neural network input features. To achieve this, a hybrid method consisting of both the sensitivity and discrete Fourier transform methods are used in which the sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform method for extracting the meaningful features. To illustrate the effectiveness of the proposed methods, ATC simulations have been performed on the Malaysian power system. Neural network results shows that better ATC assessment accuracy can be obtained by selecting and extracting features using the proposed methods as compared to using only the discrete Fourier transform or the sensitivity methods. Results have also shown that the method is capable of reflecting accurate variations in load levels and effect of contingencies such as line outages. Computational time can be greatly reduced by using the neural network based ATC assessment method and, therefore, it can be used to provide a real time market signal of the capability of a transmission system in delivering power.",
keywords = "Neural network, Transfer capability, Transmission systems",
author = "Othman, {M. M.} and Azah Mohamed and Aini Hussain",
year = "2004",
month = "11",
doi = "10.1080/15325000490435874",
language = "English",
volume = "32",
pages = "1121--1136",
journal = "Electric Power Components and Systems",
issn = "1532-5008",
publisher = "Taylor and Francis Ltd.",
number = "11",

}

TY - JOUR

T1 - A neural network based ATC assessment incorporating novel feature selection and extraction methods

AU - Othman, M. M.

AU - Mohamed, Azah

AU - Hussain, Aini

PY - 2004/11

Y1 - 2004/11

N2 - This article presents a neural network based method for assessing the inter-area available transfer capability (ATC) of power systems aimed at providing a fast and accurate ATC. In the neural network implementation, the Levenberg-Marquardt modified back propagation algorithm is used in the training of the neural network so as to improve the speed and the convergence in the training process. One of the important considerations in applying neural network to transfer capability assessment is the proper selection and extraction of neural network input features. To achieve this, a hybrid method consisting of both the sensitivity and discrete Fourier transform methods are used in which the sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform method for extracting the meaningful features. To illustrate the effectiveness of the proposed methods, ATC simulations have been performed on the Malaysian power system. Neural network results shows that better ATC assessment accuracy can be obtained by selecting and extracting features using the proposed methods as compared to using only the discrete Fourier transform or the sensitivity methods. Results have also shown that the method is capable of reflecting accurate variations in load levels and effect of contingencies such as line outages. Computational time can be greatly reduced by using the neural network based ATC assessment method and, therefore, it can be used to provide a real time market signal of the capability of a transmission system in delivering power.

AB - This article presents a neural network based method for assessing the inter-area available transfer capability (ATC) of power systems aimed at providing a fast and accurate ATC. In the neural network implementation, the Levenberg-Marquardt modified back propagation algorithm is used in the training of the neural network so as to improve the speed and the convergence in the training process. One of the important considerations in applying neural network to transfer capability assessment is the proper selection and extraction of neural network input features. To achieve this, a hybrid method consisting of both the sensitivity and discrete Fourier transform methods are used in which the sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform method for extracting the meaningful features. To illustrate the effectiveness of the proposed methods, ATC simulations have been performed on the Malaysian power system. Neural network results shows that better ATC assessment accuracy can be obtained by selecting and extracting features using the proposed methods as compared to using only the discrete Fourier transform or the sensitivity methods. Results have also shown that the method is capable of reflecting accurate variations in load levels and effect of contingencies such as line outages. Computational time can be greatly reduced by using the neural network based ATC assessment method and, therefore, it can be used to provide a real time market signal of the capability of a transmission system in delivering power.

KW - Neural network

KW - Transfer capability

KW - Transmission systems

UR - http://www.scopus.com/inward/record.url?scp=8644224839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8644224839&partnerID=8YFLogxK

U2 - 10.1080/15325000490435874

DO - 10.1080/15325000490435874

M3 - Article

AN - SCOPUS:8644224839

VL - 32

SP - 1121

EP - 1136

JO - Electric Power Components and Systems

JF - Electric Power Components and Systems

SN - 1532-5008

IS - 11

ER -