Publication:
Using smart persistence and random forests to predict photovoltaic energy production

dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorHuertas Tato, Javier
dc.contributor.authorCenteno Brito, Miguel
dc.contributor.funderMinisterio de Ciencia e Innovación (España)es
dc.date.accessioned2023-09-01T13:18:38Z
dc.date.available2023-09-01T13:18:38Z
dc.date.issued2019-01-01
dc.descriptionThis article belongs to the Special Issue Solar and Wind Energy Forecasting.en
dc.description.abstractSolar energy forecasting is an active research problem and a key issue to increase the competitiveness of solar power plants in the energy market. However, using meteorological, production, or irradiance data from the past is not enough to produce accurate forecasts. This article aims to integrate a prediction algorithm (Smart Persistence), irradiance, and past production data, using a state-of-the-art machine learning technique (Random Forests). Three years of data from six solar PV modules at Faro (Portugal) are analyzed. A set of features that combines past data, predictions, averages, and variances is proposed for training and validation. The experimental results show that using Smart Persistence as a Machine Learning input greatly improves the accuracy of short-term forecasts, achieving an NRMSE of 0.25 on the best panels at short horizons and 0.33 on a 6 h horizon.en
dc.format.extent12
dc.identifier.bibliographicCitationHuertas-Tato, J., & Brito, M. (2019). Using smart persistence and random forests to predict photovoltaic energy production. Energies, 12(1), 100.en
dc.identifier.doihttps://doi.org/10.3390/en12010100
dc.identifier.issn1996-1073
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue1, 100
dc.identifier.publicationlastpage12
dc.identifier.publicationtitleEnergiesen
dc.identifier.publicationvolume12
dc.identifier.urihttps://hdl.handle.net/10016/38190
dc.identifier.uxxiAR/0000023403
dc.language.isoengen
dc.publisherMDPIen
dc.relation.projectIDGobierno de España. ENE2014-56126-C2-2-Res
dc.rights© 2018 by the authors.en
dc.rightsAtribución 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subject.ecienciaInformáticaes
dc.subject.otherSmart persistenceen
dc.subject.otherPhotovoltaic forecastingen
dc.subject.otherRandom forestsen
dc.subject.otherSolar irradianceen
dc.subject.otherForecasting methodsen
dc.subject.otherModelen
dc.titleUsing smart persistence and random forests to predict photovoltaic energy productionen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Smart_E_2019.pdf
Size:
1.32 MB
Format:
Adobe Portable Document Format