Short-term electricity load forecasting with machine learning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
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/10400.1/15267 |
Resumo: | An accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting. |
id |
RCAP_e8ab72c5ba38372d0654de524f6593cf |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/15267 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Short-term electricity load forecasting with machine learningShort-term load forecastingElectricity marketMachine learningWeekly forecastElectricityAn accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.MDPISapientiaAguilar Madrid, ErnestoAntónio, Nuno2021-03-22T14:58:22Z20212021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/15267eng10.3390/info12020050info: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:RCAAP2023-07-24T10:27:41Zoai:sapientia.ualg.pt:10400.1/15267Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:06:08.101164Repositório 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 |
Short-term electricity load forecasting with machine learning |
title |
Short-term electricity load forecasting with machine learning |
spellingShingle |
Short-term electricity load forecasting with machine learning Aguilar Madrid, Ernesto Short-term load forecasting Electricity market Machine learning Weekly forecast Electricity |
title_short |
Short-term electricity load forecasting with machine learning |
title_full |
Short-term electricity load forecasting with machine learning |
title_fullStr |
Short-term electricity load forecasting with machine learning |
title_full_unstemmed |
Short-term electricity load forecasting with machine learning |
title_sort |
Short-term electricity load forecasting with machine learning |
author |
Aguilar Madrid, Ernesto |
author_facet |
Aguilar Madrid, Ernesto António, Nuno |
author_role |
author |
author2 |
António, Nuno |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Aguilar Madrid, Ernesto António, Nuno |
dc.subject.por.fl_str_mv |
Short-term load forecasting Electricity market Machine learning Weekly forecast Electricity |
topic |
Short-term load forecasting Electricity market Machine learning Weekly forecast Electricity |
description |
An accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-03-22T14:58:22Z 2021 2021-01-01T00:00:00Z |
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/10400.1/15267 |
url |
http://hdl.handle.net/10400.1/15267 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.3390/info12020050 |
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 |
MDPI |
publisher.none.fl_str_mv |
MDPI |
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_ |
1799133302486990848 |