No Cover Image

Journal article 817 views 102 downloads

Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models

Eugenio Borghini, Cinzia Giannetti Orcid Logo

Engineering Proceedings, Volume: 5, Issue: 1, Start page: 6

Swansea University Authors: Eugenio Borghini, Cinzia Giannetti Orcid Logo

  • 57695.pdf

    PDF | Version of Record

    © 2021 by the authors.This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license

    Download (463.87KB)

Check full text

DOI (Published version): 10.3390/engproc2021005006

Abstract

Electric load forecasting is becoming increasingly challenging due to the growing penetration of decentralised energy generation and power-electronics based loads such as heat pumps and electric vehicles, which adds to a transition to more variable work patterns (accentuated by the COVID-19 pandemic...

Full description

Published in: Engineering Proceedings
ISSN: 2673-4591
Published: MDPI AG 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57695
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-09-21T12:52:09Z
last_indexed 2021-09-22T03:21:07Z
id cronfa57695
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-09-21T13:55:05.4470448</datestamp><bib-version>v2</bib-version><id>57695</id><entry>2021-08-26</entry><title>Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models</title><swanseaauthors><author><sid>f4f3adbe64cb98a2d80004d570ad786c</sid><firstname>Eugenio</firstname><surname>Borghini</surname><name>Eugenio Borghini</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-08-26</date><deptcode>MECH</deptcode><abstract>Electric load forecasting is becoming increasingly challenging due to the growing penetration of decentralised energy generation and power-electronics based loads such as heat pumps and electric vehicles, which adds to a transition to more variable work patterns (accentuated by the COVID-19 pandemic in 2020). In this paper, three different Machine Leaning models are analysed to predict the energy load one week ahead for a period of time including the COVID-19 pandemic. It is shown that, by using the recently proposed TabNet model architecture, it is possible to achieve an accuracy comparable to more traditional approaches based on gradient boosting and artificial neural networks without the need of performing complex feature engineering.</abstract><type>Journal Article</type><journal>Engineering Proceedings</journal><volume>5</volume><journalNumber>1</journalNumber><paginationStart>6</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2673-4591</issnElectronic><keywords>short-term electricity demand forecasting; neural networks; TabNet</keywords><publishedDay>25</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-06-25</publishedDate><doi>10.3390/engproc2021005006</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research was funded by the UK Engineering and Physical Sciences Research Council (EPSRC) project EP/S001387/1 and the European Regional Development Funds projects IMPACT</funders><lastEdited>2021-09-21T13:55:05.4470448</lastEdited><Created>2021-08-26T21:37:18.7846489</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Eugenio</firstname><surname>Borghini</surname><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author></authors><documents><document><filename>57695__20956__d4e36d57e35640fbaa7109345fd08038.pdf</filename><originalFilename>57695.pdf</originalFilename><uploaded>2021-09-21T13:54:02.8515988</uploaded><type>Output</type><contentLength>475002</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 by the authors.This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-09-21T13:55:05.4470448 v2 57695 2021-08-26 Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models f4f3adbe64cb98a2d80004d570ad786c Eugenio Borghini Eugenio Borghini true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2021-08-26 MECH Electric load forecasting is becoming increasingly challenging due to the growing penetration of decentralised energy generation and power-electronics based loads such as heat pumps and electric vehicles, which adds to a transition to more variable work patterns (accentuated by the COVID-19 pandemic in 2020). In this paper, three different Machine Leaning models are analysed to predict the energy load one week ahead for a period of time including the COVID-19 pandemic. It is shown that, by using the recently proposed TabNet model architecture, it is possible to achieve an accuracy comparable to more traditional approaches based on gradient boosting and artificial neural networks without the need of performing complex feature engineering. Journal Article Engineering Proceedings 5 1 6 MDPI AG 2673-4591 short-term electricity demand forecasting; neural networks; TabNet 25 6 2021 2021-06-25 10.3390/engproc2021005006 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University This research was funded by the UK Engineering and Physical Sciences Research Council (EPSRC) project EP/S001387/1 and the European Regional Development Funds projects IMPACT 2021-09-21T13:55:05.4470448 2021-08-26T21:37:18.7846489 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Eugenio Borghini 1 Cinzia Giannetti 0000-0003-0339-5872 2 57695__20956__d4e36d57e35640fbaa7109345fd08038.pdf 57695.pdf 2021-09-21T13:54:02.8515988 Output 475002 application/pdf Version of Record true © 2021 by the authors.This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license true eng https://creativecommons.org/licenses/by/4.0/
title Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
spellingShingle Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
Eugenio Borghini
Cinzia Giannetti
title_short Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
title_full Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
title_fullStr Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
title_full_unstemmed Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
title_sort Short Term Load Forecasting Using TabNet: A Comparative Study with Traditional State-of-the-Art Regression Models
author_id_str_mv f4f3adbe64cb98a2d80004d570ad786c
a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv f4f3adbe64cb98a2d80004d570ad786c_***_Eugenio Borghini
a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author Eugenio Borghini
Cinzia Giannetti
author2 Eugenio Borghini
Cinzia Giannetti
format Journal article
container_title Engineering Proceedings
container_volume 5
container_issue 1
container_start_page 6
publishDate 2021
institution Swansea University
issn 2673-4591
doi_str_mv 10.3390/engproc2021005006
publisher MDPI AG
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description Electric load forecasting is becoming increasingly challenging due to the growing penetration of decentralised energy generation and power-electronics based loads such as heat pumps and electric vehicles, which adds to a transition to more variable work patterns (accentuated by the COVID-19 pandemic in 2020). In this paper, three different Machine Leaning models are analysed to predict the energy load one week ahead for a period of time including the COVID-19 pandemic. It is shown that, by using the recently proposed TabNet model architecture, it is possible to achieve an accuracy comparable to more traditional approaches based on gradient boosting and artificial neural networks without the need of performing complex feature engineering.
published_date 2021-06-25T04:13:37Z
_version_ 1763753923928129536
score 11.036815

Similar Items