Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/40438 |
Resumo: | The present work proposes to forecast time series of the Brazilian electricity sector. For this purpose, an attempt was made to make predictions for the Settlement Price of Differences (PLD) and the wind speed for moving wind turbines, which transforms the kinetic energy of air currents into electrical energy, based on the ARIMA methodology, based on statistics computational, and the SVM model, from the area of artificial intelligence, and the period analyzed corresponds from 2001 to 2009 for the PLD and from 2004 to 2017 for the wind. The results provide an analysis tool for the free energy market, as they demonstrate price trends and electricity production, serving as an aid to decision-making, with ARIMA being the predictive model that performed best in short-term forecasts. Despite this, it is concluded that the SVM has the potential to produce more assertive results for long-term forecasts, since the model has many characteristics that can be exploited and thus enhance forecasts with large volumes of data in more complex situations. |
id |
UNIFEI_8bee4ed41edc48a16ceaf536c51b8fa0 |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/40438 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical systemUso de ARIMA y SVM para pronósticos de series de tiempo del sistema eléctrico brasileñoUso do ARIMA e SVM para previsão de séries temporais do sistema elétrico brasileiroARIMASVMAprendizaje automáticoSerie de TiempoSector Eléctrico Brasileño.ARIMASVMAprendizado de MáquinaSéries TemporaisSetor Elétrico Brasileiro.ARIMASVMMachine LearningTime SeriesBrazilian Electric Sector.The present work proposes to forecast time series of the Brazilian electricity sector. For this purpose, an attempt was made to make predictions for the Settlement Price of Differences (PLD) and the wind speed for moving wind turbines, which transforms the kinetic energy of air currents into electrical energy, based on the ARIMA methodology, based on statistics computational, and the SVM model, from the area of artificial intelligence, and the period analyzed corresponds from 2001 to 2009 for the PLD and from 2004 to 2017 for the wind. The results provide an analysis tool for the free energy market, as they demonstrate price trends and electricity production, serving as an aid to decision-making, with ARIMA being the predictive model that performed best in short-term forecasts. Despite this, it is concluded that the SVM has the potential to produce more assertive results for long-term forecasts, since the model has many characteristics that can be exploited and thus enhance forecasts with large volumes of data in more complex situations.El presente trabajo propone pronosticar series de tiempo del sector eléctrico brasileño. Para ello se intentó realizar predicciones para el Precio de Liquidación de las Diferencias (PLD) y la velocidad del viento para los aerogeneradores en movimiento, que transforma la energía cinética de las corrientes de aire en energía eléctrica, con base en la metodología ARIMA, basada en estadísticas computacional, y el modelo SVM, del área de inteligencia artificial, y el periodo analizado corresponde del 2001 al 2009 para el PLD y del 2004 al 2017 para el eólico. Los resultados brindan una herramienta de análisis para el mercado libre de energía, ya que demuestran la evolución de los precios y la producción eléctrica, sirviendo de ayuda para la toma de decisiones, siendo ARIMA el modelo predictivo que mejor se desempeñó en los pronósticos a corto plazo. A pesar de esto, se concluye que el SVM tiene potencial para producir resultados más asertivos para pronósticos a largo plazo, ya que el modelo tiene muchas características que pueden ser explotadas y así mejorar los pronósticos con grandes volúmenes de datos en situaciones más complejas.O presente trabalho se propõe a prever séries temporais do setor elétrico brasileiro. Para tanto, procurou-se realizar previsões para o Preço de Liquidação das Diferenças (PLD) e a velocidade do vento para movimentação dos aerogeradores, que transforma a energia cinética das correntes de ar em energia elétrica, a partir da metodologia ARIMA, baseado na estatística computacional, e o modelo SVM, proveniente da área de inteligência artificial, sendo que o período analisado corresponde de 2001 a 2009 para o PLD e de 2004 a 2017 para o vento. Os resultados fornecem uma ferramenta de análise para o mercado livre de energia, na medida que demonstram tendências de preços e produção elétrica, servindo de auxílio à tomada de decisões, sendo o ARIMA, o modelo preditivo que performou melhor as previsões a curto prazo. Apesar disso, conclui-se que o SVM tem um potencial para produzir resultados mais assertivos para previsões a longo prazo, visto que o modelo tem muitas características que podem ser exploradas e assim potencializar previsões com grandes volumes de dados em situações mais complexas.Research, Society and Development2023-02-25info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/4043810.33448/rsd-v12i3.40438Research, Society and Development; Vol. 12 No. 3; e8112340438Research, Society and Development; Vol. 12 Núm. 3; e8112340438Research, Society and Development; v. 12 n. 3; e81123404382525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIporhttps://rsdjournal.org/index.php/rsd/article/view/40438/33065Copyright (c) 2023 Lucas Renan Maués Nunes; Juam Sousa Veras; João Pedro Ribeiro Silva; Thiago Nicolau Magalhães de Souza Conte; Wilker José Caminha dos Santos; Roberto Célio Limão e Oliveirahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessNunes, Lucas Renan Maués Veras, Juam Sousa Silva, João Pedro Ribeiro Conte, Thiago Nicolau Magalhães de Souza Santos, Wilker José Caminha dos Oliveira, Roberto Célio Limão e 2023-03-23T08:33:38Zoai:ojs.pkp.sfu.ca:article/40438Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2023-03-23T08:33:38Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system Uso de ARIMA y SVM para pronósticos de series de tiempo del sistema eléctrico brasileño Uso do ARIMA e SVM para previsão de séries temporais do sistema elétrico brasileiro |
title |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
spellingShingle |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system Nunes, Lucas Renan Maués ARIMA SVM Aprendizaje automático Serie de Tiempo Sector Eléctrico Brasileño. ARIMA SVM Aprendizado de Máquina Séries Temporais Setor Elétrico Brasileiro. ARIMA SVM Machine Learning Time Series Brazilian Electric Sector. |
title_short |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
title_full |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
title_fullStr |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
title_full_unstemmed |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
title_sort |
Use of ARIMA and SVM for forecasting time series of the Brazilian electrical system |
author |
Nunes, Lucas Renan Maués |
author_facet |
Nunes, Lucas Renan Maués Veras, Juam Sousa Silva, João Pedro Ribeiro Conte, Thiago Nicolau Magalhães de Souza Santos, Wilker José Caminha dos Oliveira, Roberto Célio Limão e |
author_role |
author |
author2 |
Veras, Juam Sousa Silva, João Pedro Ribeiro Conte, Thiago Nicolau Magalhães de Souza Santos, Wilker José Caminha dos Oliveira, Roberto Célio Limão e |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Nunes, Lucas Renan Maués Veras, Juam Sousa Silva, João Pedro Ribeiro Conte, Thiago Nicolau Magalhães de Souza Santos, Wilker José Caminha dos Oliveira, Roberto Célio Limão e |
dc.subject.por.fl_str_mv |
ARIMA SVM Aprendizaje automático Serie de Tiempo Sector Eléctrico Brasileño. ARIMA SVM Aprendizado de Máquina Séries Temporais Setor Elétrico Brasileiro. ARIMA SVM Machine Learning Time Series Brazilian Electric Sector. |
topic |
ARIMA SVM Aprendizaje automático Serie de Tiempo Sector Eléctrico Brasileño. ARIMA SVM Aprendizado de Máquina Séries Temporais Setor Elétrico Brasileiro. ARIMA SVM Machine Learning Time Series Brazilian Electric Sector. |
description |
The present work proposes to forecast time series of the Brazilian electricity sector. For this purpose, an attempt was made to make predictions for the Settlement Price of Differences (PLD) and the wind speed for moving wind turbines, which transforms the kinetic energy of air currents into electrical energy, based on the ARIMA methodology, based on statistics computational, and the SVM model, from the area of artificial intelligence, and the period analyzed corresponds from 2001 to 2009 for the PLD and from 2004 to 2017 for the wind. The results provide an analysis tool for the free energy market, as they demonstrate price trends and electricity production, serving as an aid to decision-making, with ARIMA being the predictive model that performed best in short-term forecasts. Despite this, it is concluded that the SVM has the potential to produce more assertive results for long-term forecasts, since the model has many characteristics that can be exploited and thus enhance forecasts with large volumes of data in more complex situations. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-02-25 |
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 |
https://rsdjournal.org/index.php/rsd/article/view/40438 10.33448/rsd-v12i3.40438 |
url |
https://rsdjournal.org/index.php/rsd/article/view/40438 |
identifier_str_mv |
10.33448/rsd-v12i3.40438 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/40438/33065 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 12 No. 3; e8112340438 Research, Society and Development; Vol. 12 Núm. 3; e8112340438 Research, Society and Development; v. 12 n. 3; e8112340438 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052619133288448 |