Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFS |
Texto Completo: | https://ri.ufs.br/handle/riufs/5018 |
Resumo: | The forecasting of gas consumption has a fundamental importance for the natural gas distribution company, since it is common for supply companies include clauses in their contracts that force the distributor companies to perform the volume programming of the natural gas to be withdrawn, these same companies are subjected to the application of penalties if the volume exceeds programmed limits previously established. Thus, in the present work has been studied the potentialities to use of predictive models based on regression, time series and artificial neural networks in forecasting gas consumption, with the intend to improved the methodologies currently used by gas distributor in the daily schedule to send to the supplier, in a scenario characterized by the predominance of industrial consumers with dissimilar characteristics. In this context, considering the potential of forecasting techniques, has been studied the gas consumption forecasting in the medium term of both the industrial consumers and the automotive segments. From these studies it was possible to identify particular types of behaviors, and the forecasting strategy most suitable approach using artificial neural networks, time series or a combination of both. To perform these studies was developed a computational tool to analyzing, parameterize and validate methods of forecasting based on historical data consumption. The results are promising because it presents boundary conditions close to actual values. |
id |
UFS-2_8bbcd77efe69b65fbf068cf3ff89ae4d |
---|---|
oai_identifier_str |
oai:ufs.br:riufs/5018 |
network_acronym_str |
UFS-2 |
network_name_str |
Repositório Institucional da UFS |
repository_id_str |
|
spelling |
Cruz, Gustavo Limahttp://lattes.cnpq.br/1368658416990415Cardoso, Carlos Alberto Villacortahttp://lattes.cnpq.br/12513408399319602017-09-26T18:08:12Z2017-09-26T18:08:12Z2012-12-20https://ri.ufs.br/handle/riufs/5018The forecasting of gas consumption has a fundamental importance for the natural gas distribution company, since it is common for supply companies include clauses in their contracts that force the distributor companies to perform the volume programming of the natural gas to be withdrawn, these same companies are subjected to the application of penalties if the volume exceeds programmed limits previously established. Thus, in the present work has been studied the potentialities to use of predictive models based on regression, time series and artificial neural networks in forecasting gas consumption, with the intend to improved the methodologies currently used by gas distributor in the daily schedule to send to the supplier, in a scenario characterized by the predominance of industrial consumers with dissimilar characteristics. In this context, considering the potential of forecasting techniques, has been studied the gas consumption forecasting in the medium term of both the industrial consumers and the automotive segments. From these studies it was possible to identify particular types of behaviors, and the forecasting strategy most suitable approach using artificial neural networks, time series or a combination of both. To perform these studies was developed a computational tool to analyzing, parameterize and validate methods of forecasting based on historical data consumption. The results are promising because it presents boundary conditions close to actual values.A previsão de consumo de gás tem fundamental importância para a companhia distribuidora de gás natural, uma vez que é comum que as empresas supridoras incluam em seus contratos cláusulas que obrigam a concessionária distribuidora realizar a programação do volume de gás natural a ser retirado, sendo a mesma submetida à aplicação de penalidades caso o volume programado exceda limites previamente estabelecidos. Sendo assim, no presente trabalho tem sido estudadas as potencialidades de utilização dos modelos de previsão baseados em regressões, séries temporais e redes neurais artificiais na previsão de consumo de gás, com o objetivo de aprimorar as metodologias atualmente utilizadas pela distribuidora de gás na programação diária realizada junto ao supridor, num cenário caracterizado pela predominância de consumidores industriais com características diferentes entre si. Neste contexto, considerando o potencial das técnicas previsão, foram realizados estudos de previsão de consumo em médio prazo de consumidores dos segmentos industrial e automotivo. A partir destes estudos foi possível identificar tipos de comportamentos particulares, bem como a estratégia de previsão mais adequada, seja utilizando as redes neurais artificiais, séries temporais ou uma combinação de ambas. Para realização dos estudos uma ferramenta computacional foi desenvolvida, a qual oferece as facilidades necessárias para analisar, parametrizar e validar os métodos de previsão baseado em dados históricos de consumo. Os resultados obtidos são promissores, pois apresentam condições de contorno próximo dos valores reais.application/pdfporUniversidade Federal de SergipePós-Graduação em Engenharia ElétricaUFSBRPrevisão de consumoSistemas de distribuiçãoGás naturalForecast of consumptionDistribution systemsNatural gasCNPQ::ENGENHARIAS::ENGENHARIA ELETRICAEstudo de técnicas de previsão de consumo em sistemas de distribuição de gás naturalStudy of consumption forecasting systems natural gas distributioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFSinstname:Universidade Federal de Sergipe (UFS)instacron:UFSORIGINALGUSTAVO_LIMA CRUZ_.pdfapplication/pdf13270601https://ri.ufs.br/jspui/bitstream/riufs/5018/1/GUSTAVO_LIMA%20CRUZ_.pdfcedcefb5a303eedc7bbcfee456ef8a06MD51TEXTGUSTAVO_LIMA CRUZ_.pdf.txtGUSTAVO_LIMA CRUZ_.pdf.txtExtracted texttext/plain139002https://ri.ufs.br/jspui/bitstream/riufs/5018/2/GUSTAVO_LIMA%20CRUZ_.pdf.txtc9b165e2ec9946e9d148ca9881412095MD52THUMBNAILGUSTAVO_LIMA CRUZ_.pdf.jpgGUSTAVO_LIMA CRUZ_.pdf.jpgGenerated Thumbnailimage/jpeg1327https://ri.ufs.br/jspui/bitstream/riufs/5018/3/GUSTAVO_LIMA%20CRUZ_.pdf.jpg6e5adbe605745839ab3447e772d06030MD53riufs/50182017-11-27 21:40:07.341oai:ufs.br:riufs/5018Repositório InstitucionalPUBhttps://ri.ufs.br/oai/requestrepositorio@academico.ufs.bropendoar:2017-11-28T00:40:07Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS)false |
dc.title.por.fl_str_mv |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
dc.title.alternative.eng.fl_str_mv |
Study of consumption forecasting systems natural gas distribution |
title |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
spellingShingle |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural Cruz, Gustavo Lima Previsão de consumo Sistemas de distribuição Gás natural Forecast of consumption Distribution systems Natural gas CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
title_short |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
title_full |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
title_fullStr |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
title_full_unstemmed |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
title_sort |
Estudo de técnicas de previsão de consumo em sistemas de distribuição de gás natural |
author |
Cruz, Gustavo Lima |
author_facet |
Cruz, Gustavo Lima |
author_role |
author |
dc.contributor.author.fl_str_mv |
Cruz, Gustavo Lima |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/1368658416990415 |
dc.contributor.advisor1.fl_str_mv |
Cardoso, Carlos Alberto Villacorta |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/1251340839931960 |
contributor_str_mv |
Cardoso, Carlos Alberto Villacorta |
dc.subject.por.fl_str_mv |
Previsão de consumo Sistemas de distribuição Gás natural |
topic |
Previsão de consumo Sistemas de distribuição Gás natural Forecast of consumption Distribution systems Natural gas CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
dc.subject.eng.fl_str_mv |
Forecast of consumption Distribution systems Natural gas |
dc.subject.cnpq.fl_str_mv |
CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA |
description |
The forecasting of gas consumption has a fundamental importance for the natural gas distribution company, since it is common for supply companies include clauses in their contracts that force the distributor companies to perform the volume programming of the natural gas to be withdrawn, these same companies are subjected to the application of penalties if the volume exceeds programmed limits previously established. Thus, in the present work has been studied the potentialities to use of predictive models based on regression, time series and artificial neural networks in forecasting gas consumption, with the intend to improved the methodologies currently used by gas distributor in the daily schedule to send to the supplier, in a scenario characterized by the predominance of industrial consumers with dissimilar characteristics. In this context, considering the potential of forecasting techniques, has been studied the gas consumption forecasting in the medium term of both the industrial consumers and the automotive segments. From these studies it was possible to identify particular types of behaviors, and the forecasting strategy most suitable approach using artificial neural networks, time series or a combination of both. To perform these studies was developed a computational tool to analyzing, parameterize and validate methods of forecasting based on historical data consumption. The results are promising because it presents boundary conditions close to actual values. |
publishDate |
2012 |
dc.date.issued.fl_str_mv |
2012-12-20 |
dc.date.accessioned.fl_str_mv |
2017-09-26T18:08:12Z |
dc.date.available.fl_str_mv |
2017-09-26T18:08:12Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://ri.ufs.br/handle/riufs/5018 |
url |
https://ri.ufs.br/handle/riufs/5018 |
dc.language.iso.fl_str_mv |
por |
language |
por |
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 |
Universidade Federal de Sergipe |
dc.publisher.program.fl_str_mv |
Pós-Graduação em Engenharia Elétrica |
dc.publisher.initials.fl_str_mv |
UFS |
dc.publisher.country.fl_str_mv |
BR |
publisher.none.fl_str_mv |
Universidade Federal de Sergipe |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFS instname:Universidade Federal de Sergipe (UFS) instacron:UFS |
instname_str |
Universidade Federal de Sergipe (UFS) |
instacron_str |
UFS |
institution |
UFS |
reponame_str |
Repositório Institucional da UFS |
collection |
Repositório Institucional da UFS |
bitstream.url.fl_str_mv |
https://ri.ufs.br/jspui/bitstream/riufs/5018/1/GUSTAVO_LIMA%20CRUZ_.pdf https://ri.ufs.br/jspui/bitstream/riufs/5018/2/GUSTAVO_LIMA%20CRUZ_.pdf.txt https://ri.ufs.br/jspui/bitstream/riufs/5018/3/GUSTAVO_LIMA%20CRUZ_.pdf.jpg |
bitstream.checksum.fl_str_mv |
cedcefb5a303eedc7bbcfee456ef8a06 c9b165e2ec9946e9d148ca9881412095 6e5adbe605745839ab3447e772d06030 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS) |
repository.mail.fl_str_mv |
repositorio@academico.ufs.br |
_version_ |
1802110826000154624 |