Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais

Detalhes bibliográficos
Autor(a) principal: Freire, Paula Karenina de Macedo Machado
Data de Publicação: 2019
Tipo de documento: Tese
Idioma: por
Título da fonte: Biblioteca Digital de Teses e Dissertações da UFPB
Texto Completo: https://repositorio.ufpb.br/jspui/handle/123456789/26404
Resumo: The economic development could be related to the quantity and quality of its water resources. Proper management of these resources is able to minimize the effects of various natural phenomena, such as droughts that directly affect the energy sector, which have recently led to blackouts in Brazil. Forecasting models are commonly used to provide better planning and operation of water supply systems. However, procedures that consider the short- to long-term forecast are still scarce in the literature, especially in the northeastern Brazil. In this way, the aim of this work was the development of robust streamflow forecasting models for different horizons (daily, monthly and annual). Eighteen models were developed, six for daily forecasting (RNAdQ→Q, RNAdP→Q, RNAdPQ→Q, WRNAdQ→Q, WRNAdP→Q e WRNAdPQ→Q); six for monthly forecasting (RNAmQ→Q, RNAmP→Q, RNAmPQ→Q, WRNAmQ→Q, WRNAmP→Q e WRNAmPQ→Q); and six for anual forecasting (RNAaQ→Q, RNAaP→Q, RNAaPQ→Q, WRNAaQ→Q, WRNAaP→Q e WRNAaPQ→Q), which were tested for streamflow forecasting to the Xingó reservoir. The efficiency of these models were tested and compared to the efficiency of the traditional models based on artificial neural networks (RNAdX, RNAmX and RNAaX), which are models that use antecedent streamflow data into Xingó reservoir to forecast future streamflow in the same reservoir. The efficiency was also tested and compared to the efficiency of the hybrid wavelet-artificial neural network models (WRNAdX, WRNAmX and WRNAaX), which are models that use antecedent streamflow data treated through the wavelet transform to forecast future streamflow in the same reservoir. The results showed that the hybrid models (WRNA) were superior to those using only artificial neural networks (RNA). Specifically, for daily forecastings, the best model was the WRNAdQ→Q hybrid model, which uses the transformed streamflows from the upstream reservoirs, as well as the combination of these streamflows, as input into the model for the streamflow forecasting in Xingó reservoir. For monthly and annual forecastings, the ideal models were the WRNAmPQ→Q and WRNAaPQ→Q hybrid models, respectively, which use the transformed precipitation over the Três Marias reservoir basin and the transformed streamflow into Xingó reservoir as input for each model to forecast the streamflow into Xingó reservoir.
id UFPB_0ce470b8376e6e10be889e1cd9827257
oai_identifier_str oai:repositorio.ufpb.br:123456789/26404
network_acronym_str UFPB
network_name_str Biblioteca Digital de Teses e Dissertações da UFPB
repository_id_str
spelling Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiaisEngenharia Civil e AmbientalPrevisão de vazãoRedes Neurais Artificiais (RNA)Transformada Wavelet Discreta (TWD)Civil and Environmental EngineeringFlow forecastArtificial Neural Networks (ANN)Discret Wavelet Transform (DWT)CNPQ::ENGENHARIAS::ENGENHARIA CIVILThe economic development could be related to the quantity and quality of its water resources. Proper management of these resources is able to minimize the effects of various natural phenomena, such as droughts that directly affect the energy sector, which have recently led to blackouts in Brazil. Forecasting models are commonly used to provide better planning and operation of water supply systems. However, procedures that consider the short- to long-term forecast are still scarce in the literature, especially in the northeastern Brazil. In this way, the aim of this work was the development of robust streamflow forecasting models for different horizons (daily, monthly and annual). Eighteen models were developed, six for daily forecasting (RNAdQ→Q, RNAdP→Q, RNAdPQ→Q, WRNAdQ→Q, WRNAdP→Q e WRNAdPQ→Q); six for monthly forecasting (RNAmQ→Q, RNAmP→Q, RNAmPQ→Q, WRNAmQ→Q, WRNAmP→Q e WRNAmPQ→Q); and six for anual forecasting (RNAaQ→Q, RNAaP→Q, RNAaPQ→Q, WRNAaQ→Q, WRNAaP→Q e WRNAaPQ→Q), which were tested for streamflow forecasting to the Xingó reservoir. The efficiency of these models were tested and compared to the efficiency of the traditional models based on artificial neural networks (RNAdX, RNAmX and RNAaX), which are models that use antecedent streamflow data into Xingó reservoir to forecast future streamflow in the same reservoir. The efficiency was also tested and compared to the efficiency of the hybrid wavelet-artificial neural network models (WRNAdX, WRNAmX and WRNAaX), which are models that use antecedent streamflow data treated through the wavelet transform to forecast future streamflow in the same reservoir. The results showed that the hybrid models (WRNA) were superior to those using only artificial neural networks (RNA). Specifically, for daily forecastings, the best model was the WRNAdQ→Q hybrid model, which uses the transformed streamflows from the upstream reservoirs, as well as the combination of these streamflows, as input into the model for the streamflow forecasting in Xingó reservoir. For monthly and annual forecastings, the ideal models were the WRNAmPQ→Q and WRNAaPQ→Q hybrid models, respectively, which use the transformed precipitation over the Três Marias reservoir basin and the transformed streamflow into Xingó reservoir as input for each model to forecast the streamflow into Xingó reservoir.NenhumaO desenvolvimento econômico de qualquer região pode estar diretamente ligado à quantidade e qualidade de seus recursos hídricos. Um gerenciamento adequado destes recursos é capaz de minimizar os efeitos de vários fenômenos naturais, tais como as secas que afetam diretamente o setor energético, o que recentemente têm provocado apagões no Brasil. Modelos de previsão são comumente usados para prover um melhor planejamento e operação de sistemas de abastecimento de água. Entretanto, procedimentos que consideram a previsão de curto a longo prazo ainda são escassos na literatura, principalmente no que diz respeito ao nordeste brasileiro. Desta forma, o objetivo deste trabalho foi o desenvolvimento de modelos robustos de previsão de vazão para diferentes horizontes (diários, mensais e anuais). Foram desenvolvidos dezoito modelos, sendo seis para previsão diária (RNAdQ→Q, RNAdP→Q, RNAdPQ→Q, WRNAdQ→Q, WRNAdP→Q e WRNAdPQ→Q); seis para previsão mensal (RNAmQ→Q, RNAmP→Q, RNAmPQ→Q, WRNAmQ→Q, WRNAmP→Q e WRNAmPQ→Q); além de seis para previsão anual (RNAaQ→Q, RNAaP→Q, RNAaPQ→Q, WRNAaQ→Q, WRNAaP→Q e WRNAaPQ→Q), os quais foram testados para previsão das vazões afluentes ao reservatório de Xingó. A eficiência desses modelos foi testada e foi comparada com a dos modelos tradicionais baseados em redes neurais artificiais (RNAdX, RNAmX e RNAaX), que são modelos que usam dados de vazão antecedente no reservatório de Xingó para prever a vazão futura no mesmo reservatório. A eficiência também foi testada e comparada com a dos modelos híbridos wavelet-redes neurais artificiais (WRNAdX, WRNAmX e WRNAaX), que são modelos que usam dados de vazão antecedente tratados através da transformada wavelet para prever a vazão futura no mesmo reservatório. Os resultados mostraram que os modelos híbridos (WRNA) foram superiores àqueles utilizando apenas redes neurais artificiais (RNA). De forma específica, para previsões diárias, o melhor modelo foi o híbrido WRNAdQ→Q, que utiliza as vazões transformadas dos reservatórios a montante, bem como a combinação destas vazões, como entrada no modelo para a previsão da vazão no reservatório de Xingó. Para previsões mensais e anuais, os modelos ideais foram os híbridos WRNAmPQ→Q e WRNAaPQ→Q, respectivamente, os quais utilizam a precipitação transformada ocorrida na bacia do reservatório de Três Marias e a vazão transformada no reservatório de Xingó como entrada em cada modelo para a previsão da vazão no reservatório de Xingó.Universidade Federal da ParaíbaBrasilEngenharia Civil e AmbientalPrograma de Pós-Graduação em Engenharia Civil e AmbientalUFPBSantos, Celso Augusto Guimarãeshttp://lattes.cnpq.br/4223859537570442Freire, Paula Karenina de Macedo Machado2023-03-07T19:29:12Z2022-05-232023-03-07T19:29:12Z2019-03-26info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesishttps://repositorio.ufpb.br/jspui/handle/123456789/26404porAttribution-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nd/3.0/br/info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFPBinstname:Universidade Federal da Paraíba (UFPB)instacron:UFPB2023-05-22T12:28:23Zoai:repositorio.ufpb.br:123456789/26404Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufpb.br/PUBhttp://tede.biblioteca.ufpb.br:8080/oai/requestdiretoria@ufpb.br|| diretoria@ufpb.bropendoar:2023-05-22T12:28:23Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB)false
dc.title.none.fl_str_mv Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
title Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
spellingShingle Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
Freire, Paula Karenina de Macedo Machado
Engenharia Civil e Ambiental
Previsão de vazão
Redes Neurais Artificiais (RNA)
Transformada Wavelet Discreta (TWD)
Civil and Environmental Engineering
Flow forecast
Artificial Neural Networks (ANN)
Discret Wavelet Transform (DWT)
CNPQ::ENGENHARIAS::ENGENHARIA CIVIL
title_short Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
title_full Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
title_fullStr Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
title_full_unstemmed Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
title_sort Modelos robustos de previsão de vazão baseados em Wavelets e redes neurais artificiais
author Freire, Paula Karenina de Macedo Machado
author_facet Freire, Paula Karenina de Macedo Machado
author_role author
dc.contributor.none.fl_str_mv Santos, Celso Augusto Guimarães
http://lattes.cnpq.br/4223859537570442
dc.contributor.author.fl_str_mv Freire, Paula Karenina de Macedo Machado
dc.subject.por.fl_str_mv Engenharia Civil e Ambiental
Previsão de vazão
Redes Neurais Artificiais (RNA)
Transformada Wavelet Discreta (TWD)
Civil and Environmental Engineering
Flow forecast
Artificial Neural Networks (ANN)
Discret Wavelet Transform (DWT)
CNPQ::ENGENHARIAS::ENGENHARIA CIVIL
topic Engenharia Civil e Ambiental
Previsão de vazão
Redes Neurais Artificiais (RNA)
Transformada Wavelet Discreta (TWD)
Civil and Environmental Engineering
Flow forecast
Artificial Neural Networks (ANN)
Discret Wavelet Transform (DWT)
CNPQ::ENGENHARIAS::ENGENHARIA CIVIL
description The economic development could be related to the quantity and quality of its water resources. Proper management of these resources is able to minimize the effects of various natural phenomena, such as droughts that directly affect the energy sector, which have recently led to blackouts in Brazil. Forecasting models are commonly used to provide better planning and operation of water supply systems. However, procedures that consider the short- to long-term forecast are still scarce in the literature, especially in the northeastern Brazil. In this way, the aim of this work was the development of robust streamflow forecasting models for different horizons (daily, monthly and annual). Eighteen models were developed, six for daily forecasting (RNAdQ→Q, RNAdP→Q, RNAdPQ→Q, WRNAdQ→Q, WRNAdP→Q e WRNAdPQ→Q); six for monthly forecasting (RNAmQ→Q, RNAmP→Q, RNAmPQ→Q, WRNAmQ→Q, WRNAmP→Q e WRNAmPQ→Q); and six for anual forecasting (RNAaQ→Q, RNAaP→Q, RNAaPQ→Q, WRNAaQ→Q, WRNAaP→Q e WRNAaPQ→Q), which were tested for streamflow forecasting to the Xingó reservoir. The efficiency of these models were tested and compared to the efficiency of the traditional models based on artificial neural networks (RNAdX, RNAmX and RNAaX), which are models that use antecedent streamflow data into Xingó reservoir to forecast future streamflow in the same reservoir. The efficiency was also tested and compared to the efficiency of the hybrid wavelet-artificial neural network models (WRNAdX, WRNAmX and WRNAaX), which are models that use antecedent streamflow data treated through the wavelet transform to forecast future streamflow in the same reservoir. The results showed that the hybrid models (WRNA) were superior to those using only artificial neural networks (RNA). Specifically, for daily forecastings, the best model was the WRNAdQ→Q hybrid model, which uses the transformed streamflows from the upstream reservoirs, as well as the combination of these streamflows, as input into the model for the streamflow forecasting in Xingó reservoir. For monthly and annual forecastings, the ideal models were the WRNAmPQ→Q and WRNAaPQ→Q hybrid models, respectively, which use the transformed precipitation over the Três Marias reservoir basin and the transformed streamflow into Xingó reservoir as input for each model to forecast the streamflow into Xingó reservoir.
publishDate 2019
dc.date.none.fl_str_mv 2019-03-26
2022-05-23
2023-03-07T19:29:12Z
2023-03-07T19:29:12Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/doctoralThesis
format doctoralThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://repositorio.ufpb.br/jspui/handle/123456789/26404
url https://repositorio.ufpb.br/jspui/handle/123456789/26404
dc.language.iso.fl_str_mv por
language por
dc.rights.driver.fl_str_mv Attribution-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nd/3.0/br/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nd/3.0/br/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Universidade Federal da Paraíba
Brasil
Engenharia Civil e Ambiental
Programa de Pós-Graduação em Engenharia Civil e Ambiental
UFPB
publisher.none.fl_str_mv Universidade Federal da Paraíba
Brasil
Engenharia Civil e Ambiental
Programa de Pós-Graduação em Engenharia Civil e Ambiental
UFPB
dc.source.none.fl_str_mv reponame:Biblioteca Digital de Teses e Dissertações da UFPB
instname:Universidade Federal da Paraíba (UFPB)
instacron:UFPB
instname_str Universidade Federal da Paraíba (UFPB)
instacron_str UFPB
institution UFPB
reponame_str Biblioteca Digital de Teses e Dissertações da UFPB
collection Biblioteca Digital de Teses e Dissertações da UFPB
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB)
repository.mail.fl_str_mv diretoria@ufpb.br|| diretoria@ufpb.br
_version_ 1801843007449726976