No Cover Image

Journal article 601 views 79 downloads

Incorporating causality in energy consumption forecasting using deep neural networks

Kshitij Sharma, Yogesh Dwivedi, Bhimaraya Metri

Annals of Operations Research

Swansea University Author: Yogesh Dwivedi

  • 60324_VoR.pdf

    PDF | Version of Record

    © The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License.

    Download (1.39MB)

Check full text

DOI (Published version): 10.1007/s10479-022-04857-3

Abstract

Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advan...

Full description

Published in: Annals of Operations Research
ISSN: 0254-5330 1572-9338
Published: Springer Science and Business Media LLC 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60324
first_indexed 2022-06-25T20:01:05Z
last_indexed 2024-11-14T12:17:08Z
id cronfa60324
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-05-21T19:22:25.8694399</datestamp><bib-version>v2</bib-version><id>60324</id><entry>2022-06-25</entry><title>Incorporating causality in energy consumption forecasting using deep neural networks</title><swanseaauthors><author><sid>d154596e71b99ad1285563c8fdd373d7</sid><firstname>Yogesh</firstname><surname>Dwivedi</surname><name>Yogesh Dwivedi</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-06-25</date><abstract>Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems.</abstract><type>Journal Article</type><journal>Annals of Operations Research</journal><volume>0</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0254-5330</issnPrint><issnElectronic>1572-9338</issnElectronic><keywords>Deep neural networks; Energy consumption; Forecasting; Machine learning</keywords><publishedDay>30</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-07-30</publishedDate><doi>10.1007/s10479-022-04857-3</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Swansea University</funders><projectreference/><lastEdited>2024-05-21T19:22:25.8694399</lastEdited><Created>2022-06-25T20:55:09.6670898</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Business Management</level></path><authors><author><firstname>Kshitij</firstname><surname>Sharma</surname><order>1</order></author><author><firstname>Yogesh</firstname><surname>Dwivedi</surname><order>2</order></author><author><firstname>Bhimaraya</firstname><surname>Metri</surname><order>3</order></author></authors><documents><document><filename>60324__25056__426443b666674b64a47018855818d103.pdf</filename><originalFilename>60324_VoR.pdf</originalFilename><uploaded>2022-08-31T14:33:37.0512136</uploaded><type>Output</type><contentLength>1460838</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2024-05-21T19:22:25.8694399 v2 60324 2022-06-25 Incorporating causality in energy consumption forecasting using deep neural networks d154596e71b99ad1285563c8fdd373d7 Yogesh Dwivedi Yogesh Dwivedi true false 2022-06-25 Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems. Journal Article Annals of Operations Research 0 Springer Science and Business Media LLC 0254-5330 1572-9338 Deep neural networks; Energy consumption; Forecasting; Machine learning 30 7 2022 2022-07-30 10.1007/s10479-022-04857-3 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University 2024-05-21T19:22:25.8694399 2022-06-25T20:55:09.6670898 Faculty of Humanities and Social Sciences School of Management - Business Management Kshitij Sharma 1 Yogesh Dwivedi 2 Bhimaraya Metri 3 60324__25056__426443b666674b64a47018855818d103.pdf 60324_VoR.pdf 2022-08-31T14:33:37.0512136 Output 1460838 application/pdf Version of Record true © The Author(s) 2022. This article is licensed under a Creative Commons Attribution 4.0 International License. true eng http://creativecommons.org/licenses/by/4.0/
title Incorporating causality in energy consumption forecasting using deep neural networks
spellingShingle Incorporating causality in energy consumption forecasting using deep neural networks
Yogesh Dwivedi
title_short Incorporating causality in energy consumption forecasting using deep neural networks
title_full Incorporating causality in energy consumption forecasting using deep neural networks
title_fullStr Incorporating causality in energy consumption forecasting using deep neural networks
title_full_unstemmed Incorporating causality in energy consumption forecasting using deep neural networks
title_sort Incorporating causality in energy consumption forecasting using deep neural networks
author_id_str_mv d154596e71b99ad1285563c8fdd373d7
author_id_fullname_str_mv d154596e71b99ad1285563c8fdd373d7_***_Yogesh Dwivedi
author Yogesh Dwivedi
author2 Kshitij Sharma
Yogesh Dwivedi
Bhimaraya Metri
format Journal article
container_title Annals of Operations Research
container_volume 0
publishDate 2022
institution Swansea University
issn 0254-5330
1572-9338
doi_str_mv 10.1007/s10479-022-04857-3
publisher Springer Science and Business Media LLC
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str School of Management - Business Management{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Business Management
document_store_str 1
active_str 0
description Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems.
published_date 2022-07-30T09:18:08Z
_version_ 1830271255530438656
score 11.060683

Similar Items