Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

Water flow forecasts are an essential information for energy production, management and hydropower control. Advanced actions to optimize electricity production can be taken based on predicted information. This work proposes an ensemble strategy using recurrent neural networks to generate a forecast...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Diogo F. Costa Silva, Arlindo R. Galvão Filho, Rafael V. Carvalho, Filipe de Souza L. Ribeiro, Clarimar J. Coelho
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	water flow forecasting energy ensemble model long short-term memory LSTM Technology T
Acceso en línea:	https://doaj.org/article/da34ca9e167549f990f5e9fef757e55f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da34ca9e167549f990f5e9fef757e55f
record_format	dspace
spelling	oai:doaj.org-article:da34ca9e167549f990f5e9fef757e55f2021-11-25T17:28:07ZWater Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model10.3390/en142277071996-1073https://doaj.org/article/da34ca9e167549f990f5e9fef757e55f2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/22/7707https://doaj.org/toc/1996-1073Water flow forecasts are an essential information for energy production, management and hydropower control. Advanced actions to optimize electricity production can be taken based on predicted information. This work proposes an ensemble strategy using recurrent neural networks to generate a forecast of water flow at Jirau Hydroelectric Power Plant (HPP), installed on the Madeira River in Brazil. The ensemble strategy consists of combining three long short-term memory (LSTM) networks that model the Madeira River and two of its tributaries: Mamoré and Abunã rivers. The historical data from streamflow of the Madeira river and its tributaries are used to validate the ensemble LSTM model, where each time series of river tributaries are modeled separated by LSTM models and the result used as input for another LSTM model in order to forecast the streamflow of the main river. The experimental results present low errors for training and test sets for individual LSTM networks and ensemble model. In addition, these results were compared with the operational forecasts performed by Jirau HPP. The proposed model showed better accuracy in four of the five scenarios tested, which indicates a promising approach to be explored in water flow forecasting based on river tributaries.Diogo F. Costa SilvaArlindo R. Galvão FilhoRafael V. CarvalhoFilipe de Souza L. RibeiroClarimar J. CoelhoMDPI AGarticlewater flow forecastingenergyensemble modellong short-term memoryLSTMTechnologyTENEnergies, Vol 14, Iss 7707, p 7707 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	water flow forecasting energy ensemble model long short-term memory LSTM Technology T
spellingShingle	water flow forecasting energy ensemble model long short-term memory LSTM Technology T Diogo F. Costa Silva Arlindo R. Galvão Filho Rafael V. Carvalho Filipe de Souza L. Ribeiro Clarimar J. Coelho Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
description	Water flow forecasts are an essential information for energy production, management and hydropower control. Advanced actions to optimize electricity production can be taken based on predicted information. This work proposes an ensemble strategy using recurrent neural networks to generate a forecast of water flow at Jirau Hydroelectric Power Plant (HPP), installed on the Madeira River in Brazil. The ensemble strategy consists of combining three long short-term memory (LSTM) networks that model the Madeira River and two of its tributaries: Mamoré and Abunã rivers. The historical data from streamflow of the Madeira river and its tributaries are used to validate the ensemble LSTM model, where each time series of river tributaries are modeled separated by LSTM models and the result used as input for another LSTM model in order to forecast the streamflow of the main river. The experimental results present low errors for training and test sets for individual LSTM networks and ensemble model. In addition, these results were compared with the operational forecasts performed by Jirau HPP. The proposed model showed better accuracy in four of the five scenarios tested, which indicates a promising approach to be explored in water flow forecasting based on river tributaries.
format	article
author	Diogo F. Costa Silva Arlindo R. Galvão Filho Rafael V. Carvalho Filipe de Souza L. Ribeiro Clarimar J. Coelho
author_facet	Diogo F. Costa Silva Arlindo R. Galvão Filho Rafael V. Carvalho Filipe de Souza L. Ribeiro Clarimar J. Coelho
author_sort	Diogo F. Costa Silva
title	Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
title_short	Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
title_full	Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
title_fullStr	Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
title_full_unstemmed	Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model
title_sort	water flow forecasting based on river tributaries using long short-term memory ensemble model
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/da34ca9e167549f990f5e9fef757e55f
work_keys_str_mv	AT diogofcostasilva waterflowforecastingbasedonrivertributariesusinglongshorttermmemoryensemblemodel AT arlindorgalvaofilho waterflowforecastingbasedonrivertributariesusinglongshorttermmemoryensemblemodel AT rafaelvcarvalho waterflowforecastingbasedonrivertributariesusinglongshorttermmemoryensemblemodel AT filipedesouzalribeiro waterflowforecastingbasedonrivertributariesusinglongshorttermmemoryensemblemodel AT clarimarjcoelho waterflowforecastingbasedonrivertributariesusinglongshorttermmemoryensemblemodel
_version_	1718412315473215488

Water Flow Forecasting Based on River Tributaries Using Long Short-Term Memory Ensemble Model

Ejemplares similares