Show simple item record

dc.contributor.authorManero Font, Jaume
dc.contributor.authorBéjar Alonso, Javier
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2021-06-03T11:10:00Z
dc.date.available2021-06-03T11:10:00Z
dc.date.issued2021-05-29
dc.identifier.citationManero, J.; Béjar, J. Forecastability measures that describe the complexity of a site for deep learning wind predictions. "Supercomputing frontiers and innovations", 29 Maig 2021, vol. 8, núm. 1, p. 8-27.
dc.identifier.issn2313-8734
dc.identifier.urihttp://hdl.handle.net/2117/346575
dc.description.abstractThe 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.
dc.format.extent20 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshTime-series analysis
dc.subject.lcshWind forecasting
dc.subject.otherWind time series
dc.subject.otherDeep learning
dc.subject.otherCNN
dc.subject.otherConvolutional networks
dc.subject.otherForecastability
dc.titleForecastability measures that describe the complexity of a site for deep learning wind predictions
dc.typeArticle
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacSèries temporals -- Anàlisi
dc.subject.lemacVents -- Previsió
dc.contributor.groupUniversitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
dc.identifier.doi10.14529/jsfi210102
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://superfri.org/superfri/article/view/364
dc.rights.accessOpen Access
local.identifier.drac31784421
dc.description.versionPostprint (published version)
local.citation.authorManero, J.; Béjar, J.
local.citation.publicationNameSupercomputing frontiers and innovations
local.citation.volume8
local.citation.number1
local.citation.startingPage8
local.citation.endingPage27


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial 3.0 Spain