Accuracy of wind speed predictability with heights using Recurrent Neural networks

Accurate prediction of wind speed in future time domain is critical for wind power integration into the grid. Wind speed is usually measured at lower heights while the hub heights of modern wind turbines are much higher in the range of 80-120m. This study attempts to better understand the predictabi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohandes M., Rehman S., Nuha H., Islam M.S., Schulze F.H.
Formato:	article
Lenguaje:	EN
Publicado:	University of Belgrade - Faculty of Mechanical Engineering, Belgrade 2021
Materias:	short term forecasting wind speed prediction with heights recurrent neural network multilayer perceptron Engineering (General). Civil engineering (General) TA1-2040 Mechanics of engineering. Applied mechanics TA349-359
Acceso en línea:	https://doaj.org/article/bab258c5893a47bdae92a1b8a7feff8c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bab258c5893a47bdae92a1b8a7feff8c
record_format	dspace
spelling	oai:doaj.org-article:bab258c5893a47bdae92a1b8a7feff8c2021-12-05T21:01:52ZAccuracy of wind speed predictability with heights using Recurrent Neural networks1451-20922406-128X10.5937/fme2104908Mhttps://doaj.org/article/bab258c5893a47bdae92a1b8a7feff8c2021-01-01T00:00:00Zhttps://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2021/1451-20922104908M.pdfhttps://doaj.org/toc/1451-2092https://doaj.org/toc/2406-128XAccurate prediction of wind speed in future time domain is critical for wind power integration into the grid. Wind speed is usually measured at lower heights while the hub heights of modern wind turbines are much higher in the range of 80-120m. This study attempts to better understand the predictability of wind speed with height. To achieve this, wind data was collected using Laser Illuminated Detection and Ranging (LiDAR) system at 20m, 40m, 50m, 60m, 80m, 100m, 120m, 140m, 160m, and 180m heights. This hourly averaged data is used for training and testing a Recurrent Neural Network (RNN) for the prediction of wind speed for each of the future 12 hours, using 48 previous values. Detailed analyses of short-term wind speed prediction at different heights and future hours show that wind speed is predicted more accurately at higher heights.For example, the mean absolute percent error decreases from 0.19 to 0.16as the height increase from 20m to 180m, respectively for the 12 th future hour prediction. The performance of the proposed method is compared with Multilayer Perceptron (MLP) method. Results show that RNN performed better than MLP for most of the cases presented here at the future 6th hour.Mohandes M.Rehman S.Nuha H.Islam M.S.Schulze F.H.University of Belgrade - Faculty of Mechanical Engineering, Belgradearticleshort term forecastingwind speed prediction with heightsrecurrent neural networkmultilayer perceptronEngineering (General). Civil engineering (General)TA1-2040Mechanics of engineering. Applied mechanicsTA349-359ENFME Transactions, Vol 49, Iss 4, Pp 908-918 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	short term forecasting wind speed prediction with heights recurrent neural network multilayer perceptron Engineering (General). Civil engineering (General) TA1-2040 Mechanics of engineering. Applied mechanics TA349-359
spellingShingle	short term forecasting wind speed prediction with heights recurrent neural network multilayer perceptron Engineering (General). Civil engineering (General) TA1-2040 Mechanics of engineering. Applied mechanics TA349-359 Mohandes M. Rehman S. Nuha H. Islam M.S. Schulze F.H. Accuracy of wind speed predictability with heights using Recurrent Neural networks
description	Accurate prediction of wind speed in future time domain is critical for wind power integration into the grid. Wind speed is usually measured at lower heights while the hub heights of modern wind turbines are much higher in the range of 80-120m. This study attempts to better understand the predictability of wind speed with height. To achieve this, wind data was collected using Laser Illuminated Detection and Ranging (LiDAR) system at 20m, 40m, 50m, 60m, 80m, 100m, 120m, 140m, 160m, and 180m heights. This hourly averaged data is used for training and testing a Recurrent Neural Network (RNN) for the prediction of wind speed for each of the future 12 hours, using 48 previous values. Detailed analyses of short-term wind speed prediction at different heights and future hours show that wind speed is predicted more accurately at higher heights.For example, the mean absolute percent error decreases from 0.19 to 0.16as the height increase from 20m to 180m, respectively for the 12 th future hour prediction. The performance of the proposed method is compared with Multilayer Perceptron (MLP) method. Results show that RNN performed better than MLP for most of the cases presented here at the future 6th hour.
format	article
author	Mohandes M. Rehman S. Nuha H. Islam M.S. Schulze F.H.
author_facet	Mohandes M. Rehman S. Nuha H. Islam M.S. Schulze F.H.
author_sort	Mohandes M.
title	Accuracy of wind speed predictability with heights using Recurrent Neural networks
title_short	Accuracy of wind speed predictability with heights using Recurrent Neural networks
title_full	Accuracy of wind speed predictability with heights using Recurrent Neural networks
title_fullStr	Accuracy of wind speed predictability with heights using Recurrent Neural networks
title_full_unstemmed	Accuracy of wind speed predictability with heights using Recurrent Neural networks
title_sort	accuracy of wind speed predictability with heights using recurrent neural networks
publisher	University of Belgrade - Faculty of Mechanical Engineering, Belgrade
publishDate	2021
url	https://doaj.org/article/bab258c5893a47bdae92a1b8a7feff8c
work_keys_str_mv	AT mohandesm accuracyofwindspeedpredictabilitywithheightsusingrecurrentneuralnetworks AT rehmans accuracyofwindspeedpredictabilitywithheightsusingrecurrentneuralnetworks AT nuhah accuracyofwindspeedpredictabilitywithheightsusingrecurrentneuralnetworks AT islamms accuracyofwindspeedpredictabilitywithheightsusingrecurrentneuralnetworks AT schulzefh accuracyofwindspeedpredictabilitywithheightsusingrecurrentneuralnetworks
_version_	1718371026241323008

Accuracy of wind speed predictability with heights using Recurrent Neural networks

Ejemplares similares