Implementation of artificial neural network to allocate transmission usage in bilateral trade power market

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

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper proposes a method to allocate transmission usage for simultaneous bilateral transactions using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN, utilising a conventional circuit theory method as the trainer. Based on solved load flow and followed by a procedure to decouple the line usage on the basis of transaction pairs, the description of inputs and outputs of the training data for the ANN is obtained. The structure of artificial neural network is designed to assess the extent of line usage by each generator while supplying to their respective customer. Most commonly used feedforward architecture has been chosen for the proposed ANN based transmission usage allocation technique. Almost all the system variables obtained from load flow solutions are utilized as an input to the neural network. Moreover, tan-sigmoid activation functions are incorporated in the hidden layer to realize the non linear nature of the transmission usage allocation. The proposed ANN provides promising results in terms of accuracy and computation time. A 6-bus and also the modified IEEE 14-bus network is utilized as test systems to illustrate the effectiveness of the ANN output compared to that of conventional methods.

Original languageEnglish
Pages (from-to)253-264
Number of pages12
JournalInternational Review of Electrical Engineering
Volume3
Issue number2
Publication statusPublished - Apr 2008
Externally publishedYes

Fingerprint

Neural networks
Power markets
Circuit theory
Supervised learning
Chemical activation

Keywords

  • and Transmission usage allocation
  • Artificial neural network (ANN)
  • Bilateral transactions
  • Circuit theory

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Khalid, S. N., Mustafa, M. W., Shareef, H., Khairuddin, A., Kalam, A., & Maungthan Oo, A. (2008). Implementation of artificial neural network to allocate transmission usage in bilateral trade power market. International Review of Electrical Engineering, 3(2), 253-264.

Implementation of artificial neural network to allocate transmission usage in bilateral trade power market. / Khalid, S. N.; Mustafa, M. W.; Shareef, H.; Khairuddin, A.; Kalam, A.; Maungthan Oo, A.

In: International Review of Electrical Engineering, Vol. 3, No. 2, 04.2008, p. 253-264.

Research output: Contribution to journalArticle

Khalid, SN, Mustafa, MW, Shareef, H, Khairuddin, A, Kalam, A & Maungthan Oo, A 2008, 'Implementation of artificial neural network to allocate transmission usage in bilateral trade power market', International Review of Electrical Engineering, vol. 3, no. 2, pp. 253-264.
Khalid, S. N. ; Mustafa, M. W. ; Shareef, H. ; Khairuddin, A. ; Kalam, A. ; Maungthan Oo, A. / Implementation of artificial neural network to allocate transmission usage in bilateral trade power market. In: International Review of Electrical Engineering. 2008 ; Vol. 3, No. 2. pp. 253-264.
@article{2fb7ea5f0b2f43b2a178f4f05fedf6d5,
title = "Implementation of artificial neural network to allocate transmission usage in bilateral trade power market",
abstract = "This paper proposes a method to allocate transmission usage for simultaneous bilateral transactions using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN, utilising a conventional circuit theory method as the trainer. Based on solved load flow and followed by a procedure to decouple the line usage on the basis of transaction pairs, the description of inputs and outputs of the training data for the ANN is obtained. The structure of artificial neural network is designed to assess the extent of line usage by each generator while supplying to their respective customer. Most commonly used feedforward architecture has been chosen for the proposed ANN based transmission usage allocation technique. Almost all the system variables obtained from load flow solutions are utilized as an input to the neural network. Moreover, tan-sigmoid activation functions are incorporated in the hidden layer to realize the non linear nature of the transmission usage allocation. The proposed ANN provides promising results in terms of accuracy and computation time. A 6-bus and also the modified IEEE 14-bus network is utilized as test systems to illustrate the effectiveness of the ANN output compared to that of conventional methods.",
keywords = "and Transmission usage allocation, Artificial neural network (ANN), Bilateral transactions, Circuit theory",
author = "Khalid, {S. N.} and Mustafa, {M. W.} and H. Shareef and A. Khairuddin and A. Kalam and {Maungthan Oo}, A.",
year = "2008",
month = "4",
language = "English",
volume = "3",
pages = "253--264",
journal = "International Review of Electrical Engineering",
issn = "1827-6660",
publisher = "Praise Worthy Prize",
number = "2",

}

TY - JOUR

T1 - Implementation of artificial neural network to allocate transmission usage in bilateral trade power market

AU - Khalid, S. N.

AU - Mustafa, M. W.

AU - Shareef, H.

AU - Khairuddin, A.

AU - Kalam, A.

AU - Maungthan Oo, A.

PY - 2008/4

Y1 - 2008/4

N2 - This paper proposes a method to allocate transmission usage for simultaneous bilateral transactions using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN, utilising a conventional circuit theory method as the trainer. Based on solved load flow and followed by a procedure to decouple the line usage on the basis of transaction pairs, the description of inputs and outputs of the training data for the ANN is obtained. The structure of artificial neural network is designed to assess the extent of line usage by each generator while supplying to their respective customer. Most commonly used feedforward architecture has been chosen for the proposed ANN based transmission usage allocation technique. Almost all the system variables obtained from load flow solutions are utilized as an input to the neural network. Moreover, tan-sigmoid activation functions are incorporated in the hidden layer to realize the non linear nature of the transmission usage allocation. The proposed ANN provides promising results in terms of accuracy and computation time. A 6-bus and also the modified IEEE 14-bus network is utilized as test systems to illustrate the effectiveness of the ANN output compared to that of conventional methods.

AB - This paper proposes a method to allocate transmission usage for simultaneous bilateral transactions using artificial neural network (ANN). The basic idea is to use supervised learning paradigm to train the ANN, utilising a conventional circuit theory method as the trainer. Based on solved load flow and followed by a procedure to decouple the line usage on the basis of transaction pairs, the description of inputs and outputs of the training data for the ANN is obtained. The structure of artificial neural network is designed to assess the extent of line usage by each generator while supplying to their respective customer. Most commonly used feedforward architecture has been chosen for the proposed ANN based transmission usage allocation technique. Almost all the system variables obtained from load flow solutions are utilized as an input to the neural network. Moreover, tan-sigmoid activation functions are incorporated in the hidden layer to realize the non linear nature of the transmission usage allocation. The proposed ANN provides promising results in terms of accuracy and computation time. A 6-bus and also the modified IEEE 14-bus network is utilized as test systems to illustrate the effectiveness of the ANN output compared to that of conventional methods.

KW - and Transmission usage allocation

KW - Artificial neural network (ANN)

KW - Bilateral transactions

KW - Circuit theory

UR - http://www.scopus.com/inward/record.url?scp=65849275896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65849275896&partnerID=8YFLogxK

M3 - Article

VL - 3

SP - 253

EP - 264

JO - International Review of Electrical Engineering

JF - International Review of Electrical Engineering

SN - 1827-6660

IS - 2

ER -