Electricity consumption forecasting in Brazilian northeastern region
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista de Engenharia e Pesquisa Aplicada |
Texto Completo: | http://revistas.poli.br/index.php/repa/article/view/1684 |
Resumo: | Electric power systems collect large volumes of data that can provide valuable information on energy consumption. Electric utilities can use this historical consumption data to assist in the decision-making process with regard to energy production, through estimating the expected energy consumption. In this work, the energy consumption forecasting problem was modeled as being univariate with a temporal step forward. The algorithms: Naive (Persistent, Mean and Median), SARIMA, MLP, CNN and LSTM were used; and a greedy search of its hyperparameters was performed in order to find the best configuration associated with each algorithm. In addition, for comparison and choice of the best forecasting algorithm, the MAPE metric and the modified Deibold-Mariano hypothesis test were used. For the proof of concept of the methodological proposal, energy consumption data from the Northeast region of Brazil between the years 2004 to 2019 were used. |
id |
UFPE-2_bfc6b134c875bcbc9a6e84e79e76c910 |
---|---|
oai_identifier_str |
oai:ojs.poli.br:article/1684 |
network_acronym_str |
UFPE-2 |
network_name_str |
Revista de Engenharia e Pesquisa Aplicada |
repository_id_str |
|
spelling |
Electricity consumption forecasting in Brazilian northeastern regionPrevisão do Consumo de Energia Elétrica na Região Nordeste do BrasilElectric power systems collect large volumes of data that can provide valuable information on energy consumption. Electric utilities can use this historical consumption data to assist in the decision-making process with regard to energy production, through estimating the expected energy consumption. In this work, the energy consumption forecasting problem was modeled as being univariate with a temporal step forward. The algorithms: Naive (Persistent, Mean and Median), SARIMA, MLP, CNN and LSTM were used; and a greedy search of its hyperparameters was performed in order to find the best configuration associated with each algorithm. In addition, for comparison and choice of the best forecasting algorithm, the MAPE metric and the modified Deibold-Mariano hypothesis test were used. For the proof of concept of the methodological proposal, energy consumption data from the Northeast region of Brazil between the years 2004 to 2019 were used.Sistemas elétricos de potência coletam grandes volumes de dados que podem fornecer informações valiosas sobre o consumo de energia. As empresas elétricas podem usar esses dados históricos de consumo para auxílio no processo de tomada de decisões no que diz respeito ao planejamento da produção de energia, principalmente pelo lado da demanda (consumo de energia esperado). Neste trabalho o problema de previsão de consumo de energia foi modelado como sendo univariado com um passo temporal à frente. Foram utilizados os algoritmos Naive (Persistente, Média e Mediana), SARIMA, MLP, CNN e LSTM; e foi desempenhada uma busca gulosa de seus hiperparâmetros com o objetivo de encontrar a melhor configuração associada a cada algoritmo. Além disso, para comparação e escolha do melhor algoritmo de previsão foi utilizado a métrica MAPE e o teste de hipótese de Deibold-Mariano modificado. Para a prova de conceito da proposta metodológica, foram usados dados de consumo de energia da região Nordeste do Brasil entre os anos de 2004 a 2019.Escola Politécnica de Pernambuco2021-04-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdftext/htmlhttp://revistas.poli.br/index.php/repa/article/view/168410.25286/repa.v6i3.1684Journal of Engineering and Applied Research; Vol 6 No 3 (2021): Edição Especial em Ciência de Dados e Analytics; 21-30Revista de Engenharia e Pesquisa Aplicada; v. 6 n. 3 (2021): Edição Especial em Ciência de Dados e Analytics; 21-302525-425110.25286/repa.v6i3reponame:Revista de Engenharia e Pesquisa Aplicadainstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEporhttp://revistas.poli.br/index.php/repa/article/view/1684/730http://revistas.poli.br/index.php/repa/article/view/1684/731Copyright (c) 2021 Iván Patricio Marcos, Armando Pereira Pontes Júniorhttp://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessMarcos, Iván PatricioPontes Júnior, Armando Pereira2021-07-13T08:40:30Zoai:ojs.poli.br:article/1684Revistahttp://revistas.poli.br/index.php/repaONGhttp://revistas.poli.br/index.php/repa/oai||repa@poli.br2525-42512525-4251opendoar:2021-07-13T08:40:30Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE)false |
dc.title.none.fl_str_mv |
Electricity consumption forecasting in Brazilian northeastern region Previsão do Consumo de Energia Elétrica na Região Nordeste do Brasil |
title |
Electricity consumption forecasting in Brazilian northeastern region |
spellingShingle |
Electricity consumption forecasting in Brazilian northeastern region Marcos, Iván Patricio |
title_short |
Electricity consumption forecasting in Brazilian northeastern region |
title_full |
Electricity consumption forecasting in Brazilian northeastern region |
title_fullStr |
Electricity consumption forecasting in Brazilian northeastern region |
title_full_unstemmed |
Electricity consumption forecasting in Brazilian northeastern region |
title_sort |
Electricity consumption forecasting in Brazilian northeastern region |
author |
Marcos, Iván Patricio |
author_facet |
Marcos, Iván Patricio Pontes Júnior, Armando Pereira |
author_role |
author |
author2 |
Pontes Júnior, Armando Pereira |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Marcos, Iván Patricio Pontes Júnior, Armando Pereira |
description |
Electric power systems collect large volumes of data that can provide valuable information on energy consumption. Electric utilities can use this historical consumption data to assist in the decision-making process with regard to energy production, through estimating the expected energy consumption. In this work, the energy consumption forecasting problem was modeled as being univariate with a temporal step forward. The algorithms: Naive (Persistent, Mean and Median), SARIMA, MLP, CNN and LSTM were used; and a greedy search of its hyperparameters was performed in order to find the best configuration associated with each algorithm. In addition, for comparison and choice of the best forecasting algorithm, the MAPE metric and the modified Deibold-Mariano hypothesis test were used. For the proof of concept of the methodological proposal, energy consumption data from the Northeast region of Brazil between the years 2004 to 2019 were used. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-04-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/1684 10.25286/repa.v6i3.1684 |
url |
http://revistas.poli.br/index.php/repa/article/view/1684 |
identifier_str_mv |
10.25286/repa.v6i3.1684 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/1684/730 http://revistas.poli.br/index.php/repa/article/view/1684/731 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2021 Iván Patricio Marcos, Armando Pereira Pontes Júnior http://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2021 Iván Patricio Marcos, Armando Pereira Pontes Júnior http://creativecommons.org/licenses/by-nc/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf text/html |
dc.publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
dc.source.none.fl_str_mv |
Journal of Engineering and Applied Research; Vol 6 No 3 (2021): Edição Especial em Ciência de Dados e Analytics; 21-30 Revista de Engenharia e Pesquisa Aplicada; v. 6 n. 3 (2021): Edição Especial em Ciência de Dados e Analytics; 21-30 2525-4251 10.25286/repa.v6i3 reponame:Revista de Engenharia e Pesquisa Aplicada instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Revista de Engenharia e Pesquisa Aplicada |
collection |
Revista de Engenharia e Pesquisa Aplicada |
repository.name.fl_str_mv |
Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
||repa@poli.br |
_version_ |
1798036000361938944 |