Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/en13061407 http://hdl.handle.net/11449/200216 |
Resumo: | The prediction of electricity generation is one of the most important tasks in the management of modern energy systems. Improving the assertiveness of this prediction can support government agencies, electric companies, and power suppliers in minimizing the electricity cost to the end consumer. In this study, the problem of forecasting the energy demand in the Brazilian Interconnected Power Grid was addressed, by gathering different energy-related datasets taken from public Brazilian agencies into a unified and open database, used to tune three machine learning models. In contrast to several works in the Brazilian context, which provide only annual/monthly load estimations, the learning approaches Random Forest, Gradient Boosting, and Support Vector Machines were trained and optimized as new ensemble-based predictors with parameter tuning to reach accurate daily/monthly forecasts. Moreover, a detailed and in-depth exploration of energy-related data as obtained from the Brazilian power grid is also given. As shown in the validation study, the tuned predictors were effective in producing very small forecasting errors under different evaluation scenarios. |
id |
UNSP_516bb4f4d1f95aca1a6863c6aa188bb5 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/200216 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning modelsBrazilian power gridData-driven analysisEnergy forecastingMachine learningThe prediction of electricity generation is one of the most important tasks in the management of modern energy systems. Improving the assertiveness of this prediction can support government agencies, electric companies, and power suppliers in minimizing the electricity cost to the end consumer. In this study, the problem of forecasting the energy demand in the Brazilian Interconnected Power Grid was addressed, by gathering different energy-related datasets taken from public Brazilian agencies into a unified and open database, used to tune three machine learning models. In contrast to several works in the Brazilian context, which provide only annual/monthly load estimations, the learning approaches Random Forest, Gradient Boosting, and Support Vector Machines were trained and optimized as new ensemble-based predictors with parameter tuning to reach accurate daily/monthly forecasts. Moreover, a detailed and in-depth exploration of energy-related data as obtained from the Brazilian power grid is also given. As shown in the validation study, the tuned predictors were effective in producing very small forecasting errors under different evaluation scenarios.Department of Energy Engineering São Paulo State University (UNESP)Center of Mathematical Sciences Applied to Industry (CeMEAI)Faculty of Science and Technology (FCT) São Paulo State University (UNESP)Department of Energy Engineering São Paulo State University (UNESP)Faculty of Science and Technology (FCT) São Paulo State University (UNESP)Universidade Estadual Paulista (Unesp)Center of Mathematical Sciences Applied to Industry (CeMEAI)Leme, João Vitor [UNESP]Casaca, Wallace [UNESP]Colnago, Marilaine [UNESP]Dias, Maurício Araújo [UNESP]2020-12-12T02:00:42Z2020-12-12T02:00:42Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/en13061407Energies, v. 13, n. 6, 2020.1996-1073http://hdl.handle.net/11449/20021610.3390/en130614072-s2.0-85082507607Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEnergiesinfo:eu-repo/semantics/openAccess2024-06-18T18:18:16Zoai:repositorio.unesp.br:11449/200216Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:09:34.855888Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
title |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
spellingShingle |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models Leme, João Vitor [UNESP] Brazilian power grid Data-driven analysis Energy forecasting Machine learning |
title_short |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
title_full |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
title_fullStr |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
title_full_unstemmed |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
title_sort |
Towards assessing the electricity demand in Brazil: Data-driven analysis and ensemble learning models |
author |
Leme, João Vitor [UNESP] |
author_facet |
Leme, João Vitor [UNESP] Casaca, Wallace [UNESP] Colnago, Marilaine [UNESP] Dias, Maurício Araújo [UNESP] |
author_role |
author |
author2 |
Casaca, Wallace [UNESP] Colnago, Marilaine [UNESP] Dias, Maurício Araújo [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Center of Mathematical Sciences Applied to Industry (CeMEAI) |
dc.contributor.author.fl_str_mv |
Leme, João Vitor [UNESP] Casaca, Wallace [UNESP] Colnago, Marilaine [UNESP] Dias, Maurício Araújo [UNESP] |
dc.subject.por.fl_str_mv |
Brazilian power grid Data-driven analysis Energy forecasting Machine learning |
topic |
Brazilian power grid Data-driven analysis Energy forecasting Machine learning |
description |
The prediction of electricity generation is one of the most important tasks in the management of modern energy systems. Improving the assertiveness of this prediction can support government agencies, electric companies, and power suppliers in minimizing the electricity cost to the end consumer. In this study, the problem of forecasting the energy demand in the Brazilian Interconnected Power Grid was addressed, by gathering different energy-related datasets taken from public Brazilian agencies into a unified and open database, used to tune three machine learning models. In contrast to several works in the Brazilian context, which provide only annual/monthly load estimations, the learning approaches Random Forest, Gradient Boosting, and Support Vector Machines were trained and optimized as new ensemble-based predictors with parameter tuning to reach accurate daily/monthly forecasts. Moreover, a detailed and in-depth exploration of energy-related data as obtained from the Brazilian power grid is also given. As shown in the validation study, the tuned predictors were effective in producing very small forecasting errors under different evaluation scenarios. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T02:00:42Z 2020-12-12T02:00:42Z 2020-01-01 |
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://dx.doi.org/10.3390/en13061407 Energies, v. 13, n. 6, 2020. 1996-1073 http://hdl.handle.net/11449/200216 10.3390/en13061407 2-s2.0-85082507607 |
url |
http://dx.doi.org/10.3390/en13061407 http://hdl.handle.net/11449/200216 |
identifier_str_mv |
Energies, v. 13, n. 6, 2020. 1996-1073 10.3390/en13061407 2-s2.0-85082507607 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Energies |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129398875881472 |