Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections

Sea wind speed forecast is important for meteorological navigation system to keep ships in safe areas. The high volatility and uncertainty of wind make it difficult to accurately forecast multistep wind speed. This paper proposes a new decomposition-based model to forecast hourly sea wind speeds. Be...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jupeng Xie, Huajun Zhang, Linfan Liu, Mengchuan Li, Yixin Su
Formato: article
Lenguaje:EN
Publicado: Hindawi-Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/9d4e933c8e4a43738d2d1691343d4c2e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9d4e933c8e4a43738d2d1691343d4c2e
record_format dspace
spelling oai:doaj.org-article:9d4e933c8e4a43738d2d1691343d4c2e2021-11-29T00:55:44ZDecomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections1099-052610.1155/2021/2727218https://doaj.org/article/9d4e933c8e4a43738d2d1691343d4c2e2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/2727218https://doaj.org/toc/1099-0526Sea wind speed forecast is important for meteorological navigation system to keep ships in safe areas. The high volatility and uncertainty of wind make it difficult to accurately forecast multistep wind speed. This paper proposes a new decomposition-based model to forecast hourly sea wind speeds. Because mode mixing affects the accuracy of the empirical mode decomposition- (EMD-) based models, this model uses the variational mode decomposition (VMD) to alleviate this problem. To improve the accuracy of predicting subseries with high nonlinearity, this model uses stacked gate recurrent units (GRU) networks. To alleviate the degradation effect of stacked GRU, this model modifies them by adding residual connections to the deep layers. This model decomposes the nonlinear wind speed data into four subseries with different frequencies adaptively. Each stacked GRU predictor has four layers and the residual connections are added to the last two layers. The predictors have 24 inputs and 3 outputs, and the forecast is an ensemble of five predictors’ outputs. The proposed model can predict wind speed in the next 3 hours according to the past 24 hours’ wind speed data. The experiment results on three different sea areas show that the performance of this model surpasses those of a state-of-the-art model, several benchmarks, and decomposition-based models.Jupeng XieHuajun ZhangLinfan LiuMengchuan LiYixin SuHindawi-WileyarticleElectronic computers. Computer scienceQA75.5-76.95ENComplexity, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Electronic computers. Computer science
QA75.5-76.95
spellingShingle Electronic computers. Computer science
QA75.5-76.95
Jupeng Xie
Huajun Zhang
Linfan Liu
Mengchuan Li
Yixin Su
Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
description Sea wind speed forecast is important for meteorological navigation system to keep ships in safe areas. The high volatility and uncertainty of wind make it difficult to accurately forecast multistep wind speed. This paper proposes a new decomposition-based model to forecast hourly sea wind speeds. Because mode mixing affects the accuracy of the empirical mode decomposition- (EMD-) based models, this model uses the variational mode decomposition (VMD) to alleviate this problem. To improve the accuracy of predicting subseries with high nonlinearity, this model uses stacked gate recurrent units (GRU) networks. To alleviate the degradation effect of stacked GRU, this model modifies them by adding residual connections to the deep layers. This model decomposes the nonlinear wind speed data into four subseries with different frequencies adaptively. Each stacked GRU predictor has four layers and the residual connections are added to the last two layers. The predictors have 24 inputs and 3 outputs, and the forecast is an ensemble of five predictors’ outputs. The proposed model can predict wind speed in the next 3 hours according to the past 24 hours’ wind speed data. The experiment results on three different sea areas show that the performance of this model surpasses those of a state-of-the-art model, several benchmarks, and decomposition-based models.
format article
author Jupeng Xie
Huajun Zhang
Linfan Liu
Mengchuan Li
Yixin Su
author_facet Jupeng Xie
Huajun Zhang
Linfan Liu
Mengchuan Li
Yixin Su
author_sort Jupeng Xie
title Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
title_short Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
title_full Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
title_fullStr Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
title_full_unstemmed Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections
title_sort decomposition-based multistep sea wind speed forecasting using stacked gated recurrent unit improved by residual connections
publisher Hindawi-Wiley
publishDate 2021
url https://doaj.org/article/9d4e933c8e4a43738d2d1691343d4c2e
work_keys_str_mv AT jupengxie decompositionbasedmultistepseawindspeedforecastingusingstackedgatedrecurrentunitimprovedbyresidualconnections
AT huajunzhang decompositionbasedmultistepseawindspeedforecastingusingstackedgatedrecurrentunitimprovedbyresidualconnections
AT linfanliu decompositionbasedmultistepseawindspeedforecastingusingstackedgatedrecurrentunitimprovedbyresidualconnections
AT mengchuanli decompositionbasedmultistepseawindspeedforecastingusingstackedgatedrecurrentunitimprovedbyresidualconnections
AT yixinsu decompositionbasedmultistepseawindspeedforecastingusingstackedgatedrecurrentunitimprovedbyresidualconnections
_version_ 1718407786702831616