Show simple item record

dc.contributor.authorManero Font, Jaume
dc.contributor.authorBéjar Alonso, Javier
dc.contributor.authorCortés García, Claudio Ulises
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.identifier.citationManero, J.; Béjar, J.; Cortés, U. Deep learning is blowing in the wind. Deep models applied to wind prediction at turbine level. A: WindEurope Conference and Exhibition. "Journal of physics: conference series, vol. 1222, Maig 2019, article 012037". Londres: Institute of Physics (IOP), p. 1-11.
dc.description.abstractWind Energy generation depends on the existence of wind, a meteorological phenomena intermittent by nature, with the consequence of generating uncertainty on the availability of wind energy in the future. The grid stability processes require continuous forecasting of wind energy generated. Forecasting wind energy can be performed either by using weather forecast data or by projecting (or regressing) the past time-series data observations into the future. This last method is the statistical or time series approach. Wind Time Series show non-linearity and non-stationarity properties, and these two properties increase the complexity of the forecasting task using statistical methodologies. In this paper we explore the use of deep learning techniques, which can represent non-linearity, to the wind speed prediction using the largest public wind dataset available, the Wind Toolkit from the National Renewable Laboratory of the US. Several deep network architectures like Multi Layer Perceptrons, Convolutional Networks or Recurrent Networks have been tested on the 126,692 wind-sites and with the results obtained valuable comparisons and conclusions have been obtained. The distribution of the wind sites across the North American Geography has allowed to include in the analysis relationships between terrain, wind forecast complexity and deep methods. With the developed testing workbench and with the availability of the Barcelona Supercomputing Center new architectures are being developed. This work concludes with the feasibility of deep learning architectures for the wind and energy forecasting.
dc.format.extent11 p.
dc.publisherInstitute of Physics (IOP)
dc.rightsAttribution 3.0 Spain
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subjectÀrees temàtiques de la UPC::Energies::Energia eòlica
dc.subject.lcshMachine learning
dc.subject.lcshWeather forecasting
dc.subject.lcshWind power
dc.subject.otherComplex networks
dc.subject.otherNetwork architecture
dc.subject.otherTime series
dc.subject.otherConvolutional networks
dc.subject.otherLearning architectures
dc.subject.otherMeteorological phenomena
dc.subject.otherMulti-layer perceptrons
dc.subject.otherStatistical methodologies
dc.subject.otherSupercomputing centers
dc.subject.otherWind energy generation
dc.subject.otherWind speed prediction
dc.subject.otherDeep learning
dc.titleDeep learning is blowing in the wind. Deep models applied to wind prediction at turbine level
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacPrevisió del temps
dc.subject.lemacEnergia eòlica
dc.contributor.groupUniversitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
dc.description.peerreviewedPeer Reviewed
dc.rights.accessOpen Access
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 1051
local.citation.authorManero, J.; Béjar, J.; Cortés, U.
local.citation.contributorWindEurope Conference and Exhibition
local.citation.publicationNameJournal of physics: conference series, vol. 1222, Maig 2019, article 012037

Files in this item


This item appears in the following Collection(s)

Show simple item record

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