The Taguchi-neural networks approach to forecast electricity consumption

Neural networks (NN) have been widely used for electricity forecasting, but some difficulties are still found. One of those difficulties is in choosing the optimal network parameter, which are strongly important to obtain accurate result. "Trial and error" commonly used to set the paramete...

Full description

Bibliographic Details
Main Authors: M.F., Romlie, D., Purwanto, H., Agustiawan
Format: Conference or Workshop Item
Language:English
Published: 2008
Subjects:
Online Access:http://scholars.utp.edu.my/id/eprint/466/
http://scholars.utp.edu.my/id/eprint/466/1/paper.pdf
_version_ 1848658994105679872
author M.F., Romlie
D., Purwanto
H., Agustiawan
author_facet M.F., Romlie
D., Purwanto
H., Agustiawan
author_sort M.F., Romlie
building UTP Institutional Repository
collection Online Access
description Neural networks (NN) have been widely used for electricity forecasting, but some difficulties are still found. One of those difficulties is in choosing the optimal network parameter, which are strongly important to obtain accurate result. "Trial and error" commonly used to set the parameter is ineffective in terms of processing time and the accuracy. In this paper, Taguchi method is employed to optimize the accuracy of NN based prediction. This hybrid approach results in the optimal network parameters. Those are: 1 for the history length, 1 day for sampling time, and 8 nodes for hidden neurons. The method is used to predict electricity consumption in Universiti Teknologi PETRONAS (UTP), Malaysia. From the preliminary results it is found that the combined method seems to be a convincing approach. © 2008 IEEE.
first_indexed 2025-11-13T07:23:22Z
format Conference or Workshop Item
id oai:scholars.utp.edu.my:466
institution Universiti Teknologi Petronas
institution_category Local University
language English
last_indexed 2025-11-13T07:23:22Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling oai:scholars.utp.edu.my:4662017-01-19T08:26:34Z http://scholars.utp.edu.my/id/eprint/466/ The Taguchi-neural networks approach to forecast electricity consumption M.F., Romlie D., Purwanto H., Agustiawan TK Electrical engineering. Electronics Nuclear engineering Neural networks (NN) have been widely used for electricity forecasting, but some difficulties are still found. One of those difficulties is in choosing the optimal network parameter, which are strongly important to obtain accurate result. "Trial and error" commonly used to set the parameter is ineffective in terms of processing time and the accuracy. In this paper, Taguchi method is employed to optimize the accuracy of NN based prediction. This hybrid approach results in the optimal network parameters. Those are: 1 for the history length, 1 day for sampling time, and 8 nodes for hidden neurons. The method is used to predict electricity consumption in Universiti Teknologi PETRONAS (UTP), Malaysia. From the preliminary results it is found that the combined method seems to be a convincing approach. © 2008 IEEE. 2008 Conference or Workshop Item NonPeerReviewed application/pdf en http://scholars.utp.edu.my/id/eprint/466/1/paper.pdf M.F., Romlie and D., Purwanto and H., Agustiawan (2008) The Taguchi-neural networks approach to forecast electricity consumption. In: IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2008, 4 May 2008 through 7 May 2008, Niagara Falls, ON. http://www.scopus.com/inward/record.url?eid=2-s2.0-51849155634&partnerID=40&md5=a50bb783cfadc77aca6d020dcbf0b0f5
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
M.F., Romlie
D., Purwanto
H., Agustiawan
The Taguchi-neural networks approach to forecast electricity consumption
title The Taguchi-neural networks approach to forecast electricity consumption
title_full The Taguchi-neural networks approach to forecast electricity consumption
title_fullStr The Taguchi-neural networks approach to forecast electricity consumption
title_full_unstemmed The Taguchi-neural networks approach to forecast electricity consumption
title_short The Taguchi-neural networks approach to forecast electricity consumption
title_sort taguchi-neural networks approach to forecast electricity consumption
topic TK Electrical engineering. Electronics Nuclear engineering
url http://scholars.utp.edu.my/id/eprint/466/
http://scholars.utp.edu.my/id/eprint/466/
http://scholars.utp.edu.my/id/eprint/466/1/paper.pdf