Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.22/22079 |
Resumo: | The management of buildings responsible for the energy storage and control can be optimized with the support of forecasting techniques. These are essential on the finding of load consumption patterns being these last involved in decisions that analyze which forecasting technique results in more accurate predictions in each context. This paper considers two forecasting methods known as artificial neural network and k-nearest neighbor involved in the prediction of consumption of a building composed by devices recording consumption and sensors data. The forecasts are performed in five minutes periods with the forecasting technique taken into account as a potential to improve the accuracy of predictions. The decision making considers the Multi-armed Bandit in reinforcement learning context to find the best suitable algorithm in each five minutes period thus improving the predictions accuracy in forecasting. The reinforcement learning has been tested in upper confidence bound and greedy algorithms with several exploration alternatives. In the case-study, three contexts have been analyzed. |
id |
RCAP_fc32209badec9ee03b7df643691e54d5 |
---|---|
oai_identifier_str |
oai:recipp.ipp.pt:10400.22/22079 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contextsEnergy managementLearningLoad forecastMulti-armed BanditThe management of buildings responsible for the energy storage and control can be optimized with the support of forecasting techniques. These are essential on the finding of load consumption patterns being these last involved in decisions that analyze which forecasting technique results in more accurate predictions in each context. This paper considers two forecasting methods known as artificial neural network and k-nearest neighbor involved in the prediction of consumption of a building composed by devices recording consumption and sensors data. The forecasts are performed in five minutes periods with the forecasting technique taken into account as a potential to improve the accuracy of predictions. The decision making considers the Multi-armed Bandit in reinforcement learning context to find the best suitable algorithm in each five minutes period thus improving the predictions accuracy in forecasting. The reinforcement learning has been tested in upper confidence bound and greedy algorithms with several exploration alternatives. In the case-study, three contexts have been analyzed.The present work has been developed under the EUREKA - ITEA3 Project (ITEA-18008), Project TIoCPS (ANI|P2020 POCI-01-0247-FEDER-046182), and has received funding from European Regional Development Fund through COMPETE 2020. The work has been done also in the scope of projects UIDB/00760/2020, CEECIND/02887/2017, financed by FEDER Funds through COMPETE program and National Funds through (FCT), Portugal.ElsevierRepositório Científico do Instituto Politécnico do PortoRamos, DanielFaria, PedroGomes, LuisCampos, P.Vale, Zita2023-02-01T15:25:46Z20222022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.22/22079eng10.1016/j.egyr.2022.01.047info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-13T13:18:25Zoai:recipp.ipp.pt:10400.22/22079Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:42:08.189019Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
title |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
spellingShingle |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts Ramos, Daniel Energy management Learning Load forecast Multi-armed Bandit |
title_short |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
title_full |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
title_fullStr |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
title_full_unstemmed |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
title_sort |
Selection of features in reinforcement learning applied to energy consumption forecast in buildings according to different contexts |
author |
Ramos, Daniel |
author_facet |
Ramos, Daniel Faria, Pedro Gomes, Luis Campos, P. Vale, Zita |
author_role |
author |
author2 |
Faria, Pedro Gomes, Luis Campos, P. Vale, Zita |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Repositório Científico do Instituto Politécnico do Porto |
dc.contributor.author.fl_str_mv |
Ramos, Daniel Faria, Pedro Gomes, Luis Campos, P. Vale, Zita |
dc.subject.por.fl_str_mv |
Energy management Learning Load forecast Multi-armed Bandit |
topic |
Energy management Learning Load forecast Multi-armed Bandit |
description |
The management of buildings responsible for the energy storage and control can be optimized with the support of forecasting techniques. These are essential on the finding of load consumption patterns being these last involved in decisions that analyze which forecasting technique results in more accurate predictions in each context. This paper considers two forecasting methods known as artificial neural network and k-nearest neighbor involved in the prediction of consumption of a building composed by devices recording consumption and sensors data. The forecasts are performed in five minutes periods with the forecasting technique taken into account as a potential to improve the accuracy of predictions. The decision making considers the Multi-armed Bandit in reinforcement learning context to find the best suitable algorithm in each five minutes period thus improving the predictions accuracy in forecasting. The reinforcement learning has been tested in upper confidence bound and greedy algorithms with several exploration alternatives. In the case-study, three contexts have been analyzed. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022 2022-01-01T00:00:00Z 2023-02-01T15:25:46Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.22/22079 |
url |
http://hdl.handle.net/10400.22/22079 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1016/j.egyr.2022.01.047 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799131507937247232 |