A novel reactive power transfer allocation method with the application of artificial neural network

S. N. Khalid, M. W. Mustafa, H. Shareef, A. Khairuddin, A. Kalam, A. Maungthan

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

Abstract

This paper proposes a novel method to identify the reactive power transfer between generators and load using modified nodal equations. Based on the solved load flow solution and the network parameters, the method partitioned the Y-bus matrix to decompose the current of the load buses as a function of the generator's current and voltage. These decomposed currents are then used independently to obtain the decomposed load reactive power. The validation of the proposed methodology is demonstrated by using a simple 5-bus system. It further focuses on creating an appropriate artificial neural network (ANN) for actual 25-bus equivalent power system of south Malaysia to illustrate the effectiveness of the ANN output compared to that of the modified nodal equations method. The basic idea is to use supervised learning paradigm to train the ANN. Most commonly used feedforward architecture has been chosen for the proposed ANN reactive power transfer allocation technique. The descriptions of inputs and outputs of the training data for the ANN is easily obtained from the load flow results and developed reactive power transfer allocation method using modified nodal equations respectively. Almost all system variables obtained from load flow solutions are utilized as an input to the neural network. The ANN output provides promising results in terms of accuracy and computation time.

Original languageEnglish
Title of host publication2008 Australasian Universities Power Engineering Conference, AUPEC 2008
Publication statusPublished - 2008
Externally publishedYes
Event2008 Australasian Universities Power Engineering Conference, AUPEC 2008 - Sydney, NSW
Duration: 14 Dec 200817 Dec 2008

Other

Other2008 Australasian Universities Power Engineering Conference, AUPEC 2008
CitySydney, NSW
Period14/12/0817/12/08

Fingerprint

Reactive power
Neural networks
Supervised learning
Electric potential

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Khalid, S. N., Mustafa, M. W., Shareef, H., Khairuddin, A., Kalam, A., & Maungthan, A. (2008). A novel reactive power transfer allocation method with the application of artificial neural network. In 2008 Australasian Universities Power Engineering Conference, AUPEC 2008 [4812968]

A novel reactive power transfer allocation method with the application of artificial neural network. / Khalid, S. N.; Mustafa, M. W.; Shareef, H.; Khairuddin, A.; Kalam, A.; Maungthan, A.

2008 Australasian Universities Power Engineering Conference, AUPEC 2008. 2008. 4812968.

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

Khalid, SN, Mustafa, MW, Shareef, H, Khairuddin, A, Kalam, A & Maungthan, A 2008, A novel reactive power transfer allocation method with the application of artificial neural network. in 2008 Australasian Universities Power Engineering Conference, AUPEC 2008., 4812968, 2008 Australasian Universities Power Engineering Conference, AUPEC 2008, Sydney, NSW, 14/12/08.
Khalid SN, Mustafa MW, Shareef H, Khairuddin A, Kalam A, Maungthan A. A novel reactive power transfer allocation method with the application of artificial neural network. In 2008 Australasian Universities Power Engineering Conference, AUPEC 2008. 2008. 4812968
Khalid, S. N. ; Mustafa, M. W. ; Shareef, H. ; Khairuddin, A. ; Kalam, A. ; Maungthan, A. / A novel reactive power transfer allocation method with the application of artificial neural network. 2008 Australasian Universities Power Engineering Conference, AUPEC 2008. 2008.
@inproceedings{47b7c0d2bff04b0eb26e02084ea6e186,
title = "A novel reactive power transfer allocation method with the application of artificial neural network",
abstract = "This paper proposes a novel method to identify the reactive power transfer between generators and load using modified nodal equations. Based on the solved load flow solution and the network parameters, the method partitioned the Y-bus matrix to decompose the current of the load buses as a function of the generator's current and voltage. These decomposed currents are then used independently to obtain the decomposed load reactive power. The validation of the proposed methodology is demonstrated by using a simple 5-bus system. It further focuses on creating an appropriate artificial neural network (ANN) for actual 25-bus equivalent power system of south Malaysia to illustrate the effectiveness of the ANN output compared to that of the modified nodal equations method. The basic idea is to use supervised learning paradigm to train the ANN. Most commonly used feedforward architecture has been chosen for the proposed ANN reactive power transfer allocation technique. The descriptions of inputs and outputs of the training data for the ANN is easily obtained from the load flow results and developed reactive power transfer allocation method using modified nodal equations respectively. Almost all system variables obtained from load flow solutions are utilized as an input to the neural network. The ANN output provides promising results in terms of accuracy and computation time.",
author = "Khalid, {S. N.} and Mustafa, {M. W.} and H. Shareef and A. Khairuddin and A. Kalam and A. Maungthan",
year = "2008",
language = "English",
isbn = "9781424441624",
booktitle = "2008 Australasian Universities Power Engineering Conference, AUPEC 2008",

}

TY - GEN

T1 - A novel reactive power transfer allocation method with the application of artificial neural network

AU - Khalid, S. N.

AU - Mustafa, M. W.

AU - Shareef, H.

AU - Khairuddin, A.

AU - Kalam, A.

AU - Maungthan, A.

PY - 2008

Y1 - 2008

N2 - This paper proposes a novel method to identify the reactive power transfer between generators and load using modified nodal equations. Based on the solved load flow solution and the network parameters, the method partitioned the Y-bus matrix to decompose the current of the load buses as a function of the generator's current and voltage. These decomposed currents are then used independently to obtain the decomposed load reactive power. The validation of the proposed methodology is demonstrated by using a simple 5-bus system. It further focuses on creating an appropriate artificial neural network (ANN) for actual 25-bus equivalent power system of south Malaysia to illustrate the effectiveness of the ANN output compared to that of the modified nodal equations method. The basic idea is to use supervised learning paradigm to train the ANN. Most commonly used feedforward architecture has been chosen for the proposed ANN reactive power transfer allocation technique. The descriptions of inputs and outputs of the training data for the ANN is easily obtained from the load flow results and developed reactive power transfer allocation method using modified nodal equations respectively. Almost all system variables obtained from load flow solutions are utilized as an input to the neural network. The ANN output provides promising results in terms of accuracy and computation time.

AB - This paper proposes a novel method to identify the reactive power transfer between generators and load using modified nodal equations. Based on the solved load flow solution and the network parameters, the method partitioned the Y-bus matrix to decompose the current of the load buses as a function of the generator's current and voltage. These decomposed currents are then used independently to obtain the decomposed load reactive power. The validation of the proposed methodology is demonstrated by using a simple 5-bus system. It further focuses on creating an appropriate artificial neural network (ANN) for actual 25-bus equivalent power system of south Malaysia to illustrate the effectiveness of the ANN output compared to that of the modified nodal equations method. The basic idea is to use supervised learning paradigm to train the ANN. Most commonly used feedforward architecture has been chosen for the proposed ANN reactive power transfer allocation technique. The descriptions of inputs and outputs of the training data for the ANN is easily obtained from the load flow results and developed reactive power transfer allocation method using modified nodal equations respectively. Almost all system variables obtained from load flow solutions are utilized as an input to the neural network. The ANN output provides promising results in terms of accuracy and computation time.

UR - http://www.scopus.com/inward/record.url?scp=67649659816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649659816&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424441624

BT - 2008 Australasian Universities Power Engineering Conference, AUPEC 2008

ER -