Identification of source to sink relationship in deregulated power systems using artificial neural network

M. W. Mustafa, Azhar B. Khairuddin, H. Shareef, S. N. Khalid

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

5 Citations (Scopus)

Abstract

This paper suggests a method to identify the relationship of real power transfer between source and sink using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN. For that a conventional power flow tracing method is used as a teacher. Based on solved load flow and followed by power tracing procedure, the description of inputs and outputs of the training data for the ANN is easily obtained. An artificial neural network is developed to assess which generators are supplying a specific load. Most commonly used feedforward architecture has been chosen for the proposed ANN power transfer allocation technique. Almost all system variables obtained from load flow solutions are utilised as an input to the neural network. Moreover, log-sigmoid activation functions are incorporated in the hidden layer to realise the non linear nature of the power flow allocation. The proposed ANN provides promising results in terms of accuracy and computation time. The IEEE 14-bus network is utilised as a test system to illustrate the effectiveness of the ANN output compared to that of conventional methods.

Original languageEnglish
Title of host publication8th International Power Engineering Conference, IPEC 2007
Pages6-11
Number of pages6
Publication statusPublished - 2007
Externally publishedYes
Event8th International Power Engineering Conference, IPEC 2007 - Singapore
Duration: 3 Dec 20076 Dec 2007

Other

Other8th International Power Engineering Conference, IPEC 2007
CitySingapore
Period3/12/076/12/07

Fingerprint

Neural networks
Supervised learning
Chemical activation

Keywords

  • Artificial neural network
  • Graph theory
  • Load flow
  • Power flow tracing

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Mustafa, M. W., Khairuddin, A. B., Shareef, H., & Khalid, S. N. (2007). Identification of source to sink relationship in deregulated power systems using artificial neural network. In 8th International Power Engineering Conference, IPEC 2007 (pp. 6-11). [4509992]

Identification of source to sink relationship in deregulated power systems using artificial neural network. / Mustafa, M. W.; Khairuddin, Azhar B.; Shareef, H.; Khalid, S. N.

8th International Power Engineering Conference, IPEC 2007. 2007. p. 6-11 4509992.

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

Mustafa, MW, Khairuddin, AB, Shareef, H & Khalid, SN 2007, Identification of source to sink relationship in deregulated power systems using artificial neural network. in 8th International Power Engineering Conference, IPEC 2007., 4509992, pp. 6-11, 8th International Power Engineering Conference, IPEC 2007, Singapore, 3/12/07.
Mustafa MW, Khairuddin AB, Shareef H, Khalid SN. Identification of source to sink relationship in deregulated power systems using artificial neural network. In 8th International Power Engineering Conference, IPEC 2007. 2007. p. 6-11. 4509992
Mustafa, M. W. ; Khairuddin, Azhar B. ; Shareef, H. ; Khalid, S. N. / Identification of source to sink relationship in deregulated power systems using artificial neural network. 8th International Power Engineering Conference, IPEC 2007. 2007. pp. 6-11
@inproceedings{cb3c716367f5445d8c34975955bed13d,
title = "Identification of source to sink relationship in deregulated power systems using artificial neural network",
abstract = "This paper suggests a method to identify the relationship of real power transfer between source and sink using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN. For that a conventional power flow tracing method is used as a teacher. Based on solved load flow and followed by power tracing procedure, the description of inputs and outputs of the training data for the ANN is easily obtained. An artificial neural network is developed to assess which generators are supplying a specific load. Most commonly used feedforward architecture has been chosen for the proposed ANN power transfer allocation technique. Almost all system variables obtained from load flow solutions are utilised as an input to the neural network. Moreover, log-sigmoid activation functions are incorporated in the hidden layer to realise the non linear nature of the power flow allocation. The proposed ANN provides promising results in terms of accuracy and computation time. The IEEE 14-bus network is utilised as a test system to illustrate the effectiveness of the ANN output compared to that of conventional methods.",
keywords = "Artificial neural network, Graph theory, Load flow, Power flow tracing",
author = "Mustafa, {M. W.} and Khairuddin, {Azhar B.} and H. Shareef and Khalid, {S. N.}",
year = "2007",
language = "English",
isbn = "9789810594237",
pages = "6--11",
booktitle = "8th International Power Engineering Conference, IPEC 2007",

}

TY - GEN

T1 - Identification of source to sink relationship in deregulated power systems using artificial neural network

AU - Mustafa, M. W.

AU - Khairuddin, Azhar B.

AU - Shareef, H.

AU - Khalid, S. N.

PY - 2007

Y1 - 2007

N2 - This paper suggests a method to identify the relationship of real power transfer between source and sink using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN. For that a conventional power flow tracing method is used as a teacher. Based on solved load flow and followed by power tracing procedure, the description of inputs and outputs of the training data for the ANN is easily obtained. An artificial neural network is developed to assess which generators are supplying a specific load. Most commonly used feedforward architecture has been chosen for the proposed ANN power transfer allocation technique. Almost all system variables obtained from load flow solutions are utilised as an input to the neural network. Moreover, log-sigmoid activation functions are incorporated in the hidden layer to realise the non linear nature of the power flow allocation. The proposed ANN provides promising results in terms of accuracy and computation time. The IEEE 14-bus network is utilised as a test system to illustrate the effectiveness of the ANN output compared to that of conventional methods.

AB - This paper suggests a method to identify the relationship of real power transfer between source and sink using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN. For that a conventional power flow tracing method is used as a teacher. Based on solved load flow and followed by power tracing procedure, the description of inputs and outputs of the training data for the ANN is easily obtained. An artificial neural network is developed to assess which generators are supplying a specific load. Most commonly used feedforward architecture has been chosen for the proposed ANN power transfer allocation technique. Almost all system variables obtained from load flow solutions are utilised as an input to the neural network. Moreover, log-sigmoid activation functions are incorporated in the hidden layer to realise the non linear nature of the power flow allocation. The proposed ANN provides promising results in terms of accuracy and computation time. The IEEE 14-bus network is utilised as a test system to illustrate the effectiveness of the ANN output compared to that of conventional methods.

KW - Artificial neural network

KW - Graph theory

KW - Load flow

KW - Power flow tracing

UR - http://www.scopus.com/inward/record.url?scp=51349168646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51349168646&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:51349168646

SN - 9789810594237

SP - 6

EP - 11

BT - 8th International Power Engineering Conference, IPEC 2007

ER -