Publicação

Dynamic artificial neural network for electricity market prices forecast

Ver documento

Detalhes bibliográficos
Resumo:This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).
Autores principais:Pinto, Tiago
Outros Autores:Sousa, Tiago; Vale, Zita
Assunto:Dynamic artificial neural network Electricity market prices forecast Artificial neural network Forecasting of electricity market prices
Ano:2012
País:Portugal
Tipo de documento:documento de conferência
Tipo de acesso:acesso restrito
Instituição associada:Instituto Politécnico do Porto
Idioma:inglês
Origem:Repositório Científico do Instituto Politécnico do Porto
_version_ 1868786083867656192
author Pinto, Tiago
author2 Sousa, Tiago
Vale, Zita
author2_role author
author
author_facet Pinto, Tiago
Sousa, Tiago
Vale, Zita
author_role author
contributor_name_str_mv REPOSITÓRIO P.PORTO
country_str PT
creators_json_txt [{\"Person.name\":\"Pinto, Tiago\",\"Person.identifier.orcid\":\"0000-0001-8248-080X\"},{\"Person.name\":\"Sousa, Tiago\"},{\"Person.name\":\"Vale, Zita\",\"Person.identifier.orcid\":\"0000-0002-4560-9544\"}]
datacite.contributors.contributor.contributorName.fl_str_mv REPOSITÓRIO P.PORTO
datacite.creators.creator.creatorName.fl_str_mv Pinto, Tiago
Sousa, Tiago
Vale, Zita
datacite.date.Accepted.fl_str_mv 2012-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2013-04-15T15:14:58Z
datacite.date.embargoed.fl_str_mv 2013-04-15T15:14:58Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_16ec
datacite.subjects.subject.fl_str_mv Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
datacite.titles.title.fl_str_mv Dynamic artificial neural network for electricity market prices forecast
dc.contributor.none.fl_str_mv REPOSITÓRIO P.PORTO
dc.creator.none.fl_str_mv Pinto, Tiago
Sousa, Tiago
Vale, Zita
dc.date.Accepted.fl_str_mv 2012-01-01T00:00:00Z
dc.date.available.fl_str_mv 2013-04-15T15:14:58Z
dc.date.embargoed.fl_str_mv 2013-04-15T15:14:58Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10400.22/1318
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv IEEE
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_16ec
dc.subject.none.fl_str_mv Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
dc.title.fl_str_mv Dynamic artificial neural network for electricity market prices forecast
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_c94f
description This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).
dirty 0
eu_rights_str_mv restrictedAccess
format conferenceObject
fulltext.url.fl_str_mv https://recipp.ipp.pt/bitstreams/95d97f66-b5d9-4294-9623-c031ac74976f/download
id recipp_d94a3b8b77ea571971300a4e1d56e34f
identifier.url.fl_str_mv http://hdl.handle.net/10400.22/1318
instacron_str recipp
institution Instituto Politécnico do Porto
instname_str Instituto Politécnico do Porto
language eng
network_acronym_str recipp
network_name_str Repositório Científico do Instituto Politécnico do Porto
oai_identifier_str oai:recipp.ipp.pt:10400.22/1318
organization_str_mv urn:organizationAcronym:recipp
person_str_mv Pinto, Tiago
Pinto, Tiago
https://www.ciencia-id.pt/2414-9B03-C4BB
2414-9B03-C4BB
http://orcid.org/0000-0001-8248-080X
0000-0001-8248-080X
Sousa, Tiago
Vale, Zita
Vale, Zita
https://www.ciencia-id.pt/721B-B0EB-7141
721B-B0EB-7141
http://orcid.org/0000-0002-4560-9544
0000-0002-4560-9544
publishDate 2012
publisher.none.fl_str_mv IEEE
reponame_str Repositório Científico do Instituto Politécnico do Porto
repository_id_str urn:repositoryAcronym:recipp
service_str_mv urn:repositoryAcronym:recipp
spelling engIEEEporThis paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).application/pdfporDynamic artificial neural network for electricity market prices forecastPersonalPinto, TiagoDSpacehttp://dspace.org/items/8d58ddc0-1023-47c0-a005-129d412ce98dDSpacehttp://dspace.org/items/8d58ddc0-1023-47c0-a005-129d412ce98dPintoTiagoCiência IDhttps://www.ciencia-id.pt2414-9B03-C4BBORCIDhttp://orcid.org0000-0001-8248-080XResearcher IDhttps://www.researcherid.comT-2245-2018Scopus Author IDhttps://www.scopus.com35219107600Sousa, TiagoPersonalVale, ZitaDSpacehttp://dspace.org/items/ff1df02d-0c0f-4db1-bf7d-78863a99420bDSpacehttp://dspace.org/items/ff1df02d-0c0f-4db1-bf7d-78863a99420bValeZitaCiência IDhttps://www.ciencia-id.pt721B-B0EB-7141ORCIDhttp://orcid.org0000-0002-4560-9544Researcher IDhttps://www.researcherid.comA-5824-2012Researcher IDhttps://www.researcherid.comN-1643-2019Scopus Author IDhttps://www.scopus.com7004115775Scopus Author IDhttps://www.scopus.com57198257978Scopus Author IDhttps://www.scopus.com57203219788HostingInstitutionOrganizationalREPOSITÓRIO P.PORTOe-mailmailto:recipp@sc.ipp.ptrecipp@sc.ipp.ptISBNIsPartOf978-1-4673-2693-3ISBNIsPartOf978-1-4673-2694-0DOIIsPartOf10.1109/INES.2012.62498502013-04-15T15:14:58Z20122013-04-11T14:45:25Z2012-01-01T00:00:00ZHandlehttp://hdl.handle.net/10400.22/1318http://purl.org/coar/access_right/c_16ecrestricted accessDynamic artificial neural networkElectricity market prices forecastArtificial neural networkForecasting of electricity market prices665561 bytesother research producthttp://purl.org/coar/resource_type/c_c94fconference objecthttp://purl.org/coar/access_right/c_16ecapplication/pdffulltexthttps://recipp.ipp.pt/bitstreams/95d97f66-b5d9-4294-9623-c031ac74976f/download16th International Conference on Intelligent Engineering Systems 2012 (INES 2012311316Lisboa
spellingShingle Dynamic artificial neural network for electricity market prices forecast
Pinto, Tiago
Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
status SINGLETON
subject.fl_str_mv Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
title Dynamic artificial neural network for electricity market prices forecast
title_full Dynamic artificial neural network for electricity market prices forecast
title_fullStr Dynamic artificial neural network for electricity market prices forecast
title_full_unstemmed Dynamic artificial neural network for electricity market prices forecast
title_short Dynamic artificial neural network for electricity market prices forecast
title_sort Dynamic artificial neural network for electricity market prices forecast
topic Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
topic_facet Dynamic artificial neural network
Electricity market prices forecast
Artificial neural network
Forecasting of electricity market prices
url http://hdl.handle.net/10400.22/1318
visible 1