No Cover Image

Conference Paper/Proceeding/Abstract 957 views

Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK

Mohammad Monfared Orcid Logo, Meghdad Fazeli Orcid Logo, Richard Lewis, Justin Searle Orcid Logo

2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)

Swansea University Authors: Mohammad Monfared Orcid Logo, Meghdad Fazeli Orcid Logo, Richard Lewis, Justin Searle Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1109/icecce49384.2020.9179454

Abstract

With the ever-increasing of PV installations, the necessity of accurate and computationally efficient day-ahead forecasts is becoming more evident, while the solution is still a real challenge. Different techniques are being employed to transform a combination of weather forecasts and historical mea...

Full description

Published in: 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)
ISBN: 978-1-7281-7117-3 9781728171166
Published: IEEE 2020
URI: https://cronfa.swan.ac.uk/Record/cronfa54786
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-08-06T13:13:16Z
last_indexed 2020-10-01T03:18:03Z
id cronfa54786
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-09-30T12:27:16.4911486</datestamp><bib-version>v2</bib-version><id>54786</id><entry>2020-07-22</entry><title>Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK</title><swanseaauthors><author><sid>adab4560ff08c8e5181ff3f12a4c36fb</sid><ORCID>0000-0002-8987-0883</ORCID><firstname>Mohammad</firstname><surname>Monfared</surname><name>Mohammad Monfared</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b7aae4026707ed626d812d07018a2113</sid><ORCID>0000-0003-1448-5339</ORCID><firstname>Meghdad</firstname><surname>Fazeli</surname><name>Meghdad Fazeli</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6b3559a0b9ac5d4048d50c09d0a5b42e</sid><firstname>Richard</firstname><surname>Lewis</surname><name>Richard Lewis</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>0e3f2c3812f181eaed11c45554d4cdd0</sid><ORCID>0000-0003-1101-075X</ORCID><firstname>Justin</firstname><surname>Searle</surname><name>Justin Searle</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2020-07-22</date><deptcode>EEEG</deptcode><abstract>With the ever-increasing of PV installations, the necessity of accurate and computationally efficient day-ahead forecasts is becoming more evident, while the solution is still a real challenge. Different techniques are being employed to transform a combination of weather forecasts and historical measurements into PV generation predictions. In this paper, the weather forecast data, provided by the UK Met Office, and the historical measurements are used to construct three different prediction models, based on linear least square regression (LSR), artificial neural network (ANN), and fuzzy. All the models can learn from new available data while running the forecasts. The results of almost one-year study show that the best perdition (for the under-study case) is achieved by averaging the forecasts from LSR and ANN.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)</journal><publisher>IEEE</publisher><isbnPrint>978-1-7281-7117-3</isbnPrint><isbnElectronic>9781728171166</isbnElectronic><keywords/><publishedDay>28</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-08-28</publishedDate><doi>10.1109/icecce49384.2020.9179454</doi><url/><notes/><college>COLLEGE NANME</college><department>Electronic and Electrical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEEG</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-09-30T12:27:16.4911486</lastEdited><Created>2020-07-22T17:39:40.5357595</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Materials Science and Engineering</level></path><authors><author><firstname>Mohammad</firstname><surname>Monfared</surname><orcid>0000-0002-8987-0883</orcid><order>1</order></author><author><firstname>Meghdad</firstname><surname>Fazeli</surname><orcid>0000-0003-1448-5339</orcid><order>2</order></author><author><firstname>Richard</firstname><surname>Lewis</surname><order>3</order></author><author><firstname>Justin</firstname><surname>Searle</surname><orcid>0000-0003-1101-075X</orcid><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2020-09-30T12:27:16.4911486 v2 54786 2020-07-22 Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK adab4560ff08c8e5181ff3f12a4c36fb 0000-0002-8987-0883 Mohammad Monfared Mohammad Monfared true false b7aae4026707ed626d812d07018a2113 0000-0003-1448-5339 Meghdad Fazeli Meghdad Fazeli true false 6b3559a0b9ac5d4048d50c09d0a5b42e Richard Lewis Richard Lewis true false 0e3f2c3812f181eaed11c45554d4cdd0 0000-0003-1101-075X Justin Searle Justin Searle true false 2020-07-22 EEEG With the ever-increasing of PV installations, the necessity of accurate and computationally efficient day-ahead forecasts is becoming more evident, while the solution is still a real challenge. Different techniques are being employed to transform a combination of weather forecasts and historical measurements into PV generation predictions. In this paper, the weather forecast data, provided by the UK Met Office, and the historical measurements are used to construct three different prediction models, based on linear least square regression (LSR), artificial neural network (ANN), and fuzzy. All the models can learn from new available data while running the forecasts. The results of almost one-year study show that the best perdition (for the under-study case) is achieved by averaging the forecasts from LSR and ANN. Conference Paper/Proceeding/Abstract 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE) IEEE 978-1-7281-7117-3 9781728171166 28 8 2020 2020-08-28 10.1109/icecce49384.2020.9179454 COLLEGE NANME Electronic and Electrical Engineering COLLEGE CODE EEEG Swansea University 2020-09-30T12:27:16.4911486 2020-07-22T17:39:40.5357595 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering Mohammad Monfared 0000-0002-8987-0883 1 Meghdad Fazeli 0000-0003-1448-5339 2 Richard Lewis 3 Justin Searle 0000-0003-1101-075X 4
title Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
spellingShingle Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
Mohammad Monfared
Meghdad Fazeli
Richard Lewis
Justin Searle
title_short Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
title_full Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
title_fullStr Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
title_full_unstemmed Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
title_sort Day-Ahead Prediction of PV Generation Using Weather Forecast Data: a Case Study in the UK
author_id_str_mv adab4560ff08c8e5181ff3f12a4c36fb
b7aae4026707ed626d812d07018a2113
6b3559a0b9ac5d4048d50c09d0a5b42e
0e3f2c3812f181eaed11c45554d4cdd0
author_id_fullname_str_mv adab4560ff08c8e5181ff3f12a4c36fb_***_Mohammad Monfared
b7aae4026707ed626d812d07018a2113_***_Meghdad Fazeli
6b3559a0b9ac5d4048d50c09d0a5b42e_***_Richard Lewis
0e3f2c3812f181eaed11c45554d4cdd0_***_Justin Searle
author Mohammad Monfared
Meghdad Fazeli
Richard Lewis
Justin Searle
author2 Mohammad Monfared
Meghdad Fazeli
Richard Lewis
Justin Searle
format Conference Paper/Proceeding/Abstract
container_title 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)
publishDate 2020
institution Swansea University
isbn 978-1-7281-7117-3
9781728171166
doi_str_mv 10.1109/icecce49384.2020.9179454
publisher IEEE
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 Engineering and Applied Sciences - Materials Science and Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Materials Science and Engineering
document_store_str 0
active_str 0
description With the ever-increasing of PV installations, the necessity of accurate and computationally efficient day-ahead forecasts is becoming more evident, while the solution is still a real challenge. Different techniques are being employed to transform a combination of weather forecasts and historical measurements into PV generation predictions. In this paper, the weather forecast data, provided by the UK Met Office, and the historical measurements are used to construct three different prediction models, based on linear least square regression (LSR), artificial neural network (ANN), and fuzzy. All the models can learn from new available data while running the forecasts. The results of almost one-year study show that the best perdition (for the under-study case) is achieved by averaging the forecasts from LSR and ANN.
published_date 2020-08-28T04:08:32Z
_version_ 1763753604345233408
score 11.013619

Similar Items