Forecastability measures that describe the complexity of a site for deep learning wind predictions

The application of deep learning to wind time series for multi-step prediction obtains good results at short horizons. The accuracy of a wind forecast is highly dependent on the specific structure of wind in the specific location, as many local features influence wind behaviour. The characterization...

ver descrição completa

Detalhes bibliográficos
Autores: Manero Font, Jaume, Béjar Alonso, Javier|||0000-0001-5281-3888
Formato: artículo
Fecha de publicación:2021
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/346575
Acesso em linha:https://hdl.handle.net/2117/346575
https://dx.doi.org/10.14529/jsfi210102
Access Level:acceso abierto
Palavra-chave:Machine learning
Time-series analysis
Wind forecasting
Wind time series
Deep learning
CNN
Convolutional networks
Forecastability
Aprenentatge automàtic
Sèries temporals -- Anàlisi
Vents -- Previsió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_69a7a522daa8d41284334ee63b5d5ffc
oai_identifier_str oai:upcommons.upc.edu:2117/346575
network_acronym_str ES
network_name_str España
repository_id_str
spelling Forecastability measures that describe the complexity of a site for deep learning wind predictionsManero Font, JaumeBéjar Alonso, Javier|||0000-0001-5281-3888Machine learningTime-series analysisWind forecastingWind time seriesDeep learningCNNConvolutional networksForecastabilityAprenentatge automàticSèries temporals -- AnàlisiVents -- PrevisióÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticThe application of deep learning to wind time series for multi-step prediction obtains good results at short horizons. The accuracy of a wind forecast is highly dependent on the specific structure of wind in the specific location, as many local features influence wind behaviour. The characterization of the complexity of a site for wind prediction is defined as forecastability or predictability and can be obtained from the inner structure of the meteorological time series observations from a site. We analyze the time series structure searching for properties that have a high correlation with the prediction result, properties that can create measures that have the potential to describe the forecastability of a site. The best measures will show a high correlation with the accuracy of the predictions. In this work, we analyze wind time series from 126,692 wind locations in the US, where we apply several deep learning methods first, and then we verify several forecastability descriptors with the accuracy deep learning results. We require High-Performance Computing (HPC) resources for this task as the deep learning algorithms have sensible resource requirements and are applied to a large set of data. The measures defined and explored in this work are based on several techniques that decompose or transform the wind time-series. By combining several of these measures, we can obtain better predictors of the site complexity, which will allow us to evaluate the future error of a prediction on this site. Forecastability measures can contribute to a wind site multi-dimensional description, becoming a valuable tool for wind resource analysts and wind forecasters.Peer Reviewed20212021-05-2920212021-06-03journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/346575https://dx.doi.org/10.14529/jsfi210102reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial 3.0 Spainhttp://creativecommons.org/licenses/by-nc/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3465752026-05-27T15:37:01Z
dc.title.none.fl_str_mv Forecastability measures that describe the complexity of a site for deep learning wind predictions
title Forecastability measures that describe the complexity of a site for deep learning wind predictions
spellingShingle Forecastability measures that describe the complexity of a site for deep learning wind predictions
Manero Font, Jaume
Machine learning
Time-series analysis
Wind forecasting
Wind time series
Deep learning
CNN
Convolutional networks
Forecastability
Aprenentatge automàtic
Sèries temporals -- Anàlisi
Vents -- Previsió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Forecastability measures that describe the complexity of a site for deep learning wind predictions
title_full Forecastability measures that describe the complexity of a site for deep learning wind predictions
title_fullStr Forecastability measures that describe the complexity of a site for deep learning wind predictions
title_full_unstemmed Forecastability measures that describe the complexity of a site for deep learning wind predictions
title_sort Forecastability measures that describe the complexity of a site for deep learning wind predictions
dc.creator.none.fl_str_mv Manero Font, Jaume
Béjar Alonso, Javier|||0000-0001-5281-3888
author Manero Font, Jaume
author_facet Manero Font, Jaume
Béjar Alonso, Javier|||0000-0001-5281-3888
author_role author
author2 Béjar Alonso, Javier|||0000-0001-5281-3888
author2_role author
dc.subject.none.fl_str_mv Machine learning
Time-series analysis
Wind forecasting
Wind time series
Deep learning
CNN
Convolutional networks
Forecastability
Aprenentatge automàtic
Sèries temporals -- Anàlisi
Vents -- Previsió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Machine learning
Time-series analysis
Wind forecasting
Wind time series
Deep learning
CNN
Convolutional networks
Forecastability
Aprenentatge automàtic
Sèries temporals -- Anàlisi
Vents -- Previsió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description The application of deep learning to wind time series for multi-step prediction obtains good results at short horizons. The accuracy of a wind forecast is highly dependent on the specific structure of wind in the specific location, as many local features influence wind behaviour. The characterization of the complexity of a site for wind prediction is defined as forecastability or predictability and can be obtained from the inner structure of the meteorological time series observations from a site. We analyze the time series structure searching for properties that have a high correlation with the prediction result, properties that can create measures that have the potential to describe the forecastability of a site. The best measures will show a high correlation with the accuracy of the predictions. In this work, we analyze wind time series from 126,692 wind locations in the US, where we apply several deep learning methods first, and then we verify several forecastability descriptors with the accuracy deep learning results. We require High-Performance Computing (HPC) resources for this task as the deep learning algorithms have sensible resource requirements and are applied to a large set of data. The measures defined and explored in this work are based on several techniques that decompose or transform the wind time-series. By combining several of these measures, we can obtain better predictors of the site complexity, which will allow us to evaluate the future error of a prediction on this site. Forecastability measures can contribute to a wind site multi-dimensional description, becoming a valuable tool for wind resource analysts and wind forecasters.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-05-29
2021
2021-06-03
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/346575
https://dx.doi.org/10.14529/jsfi210102
url https://hdl.handle.net/2117/346575
https://dx.doi.org/10.14529/jsfi210102
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial 3.0 Spain
http://creativecommons.org/licenses/by-nc/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial 3.0 Spain
http://creativecommons.org/licenses/by-nc/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410045276454912
score 15,300719

Registos relacionados