Short-term hourly load forecasting using abductive networks

Short-term load modeling and forecasting are essential for operating power utilities profitably and securely. Modern machine learning approaches, such as neural networks, have been used for this purpose. This paper proposes using the alternative technique of abductive networks, which offers the adva...

Full description

Saved in:
Bibliographic Details
Main Author: Abdel-Aal, R.E. (author)
Other Authors: unknown (author)
Format: article
Published: 2004
Subjects:
Online Access:https://eprints.kfupm.edu.sa/id/eprint/14347/1/14347_1.pdf
https://eprints.kfupm.edu.sa/id/eprint/14347/2/14347_2.doc
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513393727111168
author Abdel-Aal, R.E.
author2 unknown
author2_role author
author_facet Abdel-Aal, R.E.
unknown
author_role author
dc.creator.none.fl_str_mv Abdel-Aal, R.E.
unknown
dc.date.none.fl_str_mv 2004-02
2020
dc.format.none.fl_str_mv application/pdf
application/msword
dc.identifier.none.fl_str_mv https://eprints.kfupm.edu.sa/id/eprint/14347/1/14347_1.pdf
https://eprints.kfupm.edu.sa/id/eprint/14347/2/14347_2.doc
(2004) Short-term hourly load forecasting using abductive networks. Power Systems, IEEE Transactions on, 19.
dc.language.none.fl_str_mv en
en
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://eprints.kfupm.edu.sa/id/eprint/14347/
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Computer
dc.title.none.fl_str_mv Short-term hourly load forecasting using abductive networks
dc.type.none.fl_str_mv Article
PeerReviewed
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description Short-term load modeling and forecasting are essential for operating power utilities profitably and securely. Modern machine learning approaches, such as neural networks, have been used for this purpose. This paper proposes using the alternative technique of abductive networks, which offers the advantages of simplified and more automated model synthesis and analytical input-output models that automatically select influential inputs, provide better insight and explanations, and allow comparison with statistical and empirical models. Using hourly temperature and load data for five years, 24 dedicated models for forecasting next-day hourly loads have been developed. Evaluated on data for the sixth year, the models give an overall mean absolute percentage error (MAPE) of 2.67%. Next-hour models utilizing available load data up to the forecasting hour give a MAPE of 1.14%, outperforming neural network models for the same utility data. Two methods of accounting for the load growth trend achieve comparable performance. Effects of varying model complexity are investigated and proposals made for further improving forecasting performance.
eu_rights_str_mv openAccess
format article
id KFUPM_058aab442f71d527e581ee5b6060e8ca
identifier_str_mv (2004) Short-term hourly load forecasting using abductive networks. Power Systems, IEEE Transactions on, 19.
language_invalid_str_mv en
network_acronym_str KFUPM
network_name_str King Fahd University of Petroleum and Minerals
oai_identifier_str oai::14347
publishDate 2004
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Short-term hourly load forecasting using abductive networksAbdel-Aal, R.E.unknownComputerShort-term load modeling and forecasting are essential for operating power utilities profitably and securely. Modern machine learning approaches, such as neural networks, have been used for this purpose. This paper proposes using the alternative technique of abductive networks, which offers the advantages of simplified and more automated model synthesis and analytical input-output models that automatically select influential inputs, provide better insight and explanations, and allow comparison with statistical and empirical models. Using hourly temperature and load data for five years, 24 dedicated models for forecasting next-day hourly loads have been developed. Evaluated on data for the sixth year, the models give an overall mean absolute percentage error (MAPE) of 2.67%. Next-hour models utilizing available load data up to the forecasting hour give a MAPE of 1.14%, outperforming neural network models for the same utility data. Two methods of accounting for the load growth trend achieve comparable performance. Effects of varying model complexity are investigated and proposals made for further improving forecasting performance.IEEE2004-022020ArticlePeerReviewedinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfapplication/mswordhttps://eprints.kfupm.edu.sa/id/eprint/14347/1/14347_1.pdfhttps://eprints.kfupm.edu.sa/id/eprint/14347/2/14347_2.doc (2004) Short-term hourly load forecasting using abductive networks. Power Systems, IEEE Transactions on, 19. enenhttps://eprints.kfupm.edu.sa/id/eprint/14347/info:eu-repo/semantics/openAccessoai::143472019-11-01T14:05:25Z
spellingShingle Short-term hourly load forecasting using abductive networks
Abdel-Aal, R.E.
Computer
status_str publishedVersion
title Short-term hourly load forecasting using abductive networks
title_full Short-term hourly load forecasting using abductive networks
title_fullStr Short-term hourly load forecasting using abductive networks
title_full_unstemmed Short-term hourly load forecasting using abductive networks
title_short Short-term hourly load forecasting using abductive networks
title_sort Short-term hourly load forecasting using abductive networks
topic Computer
url https://eprints.kfupm.edu.sa/id/eprint/14347/1/14347_1.pdf
https://eprints.kfupm.edu.sa/id/eprint/14347/2/14347_2.doc