untitled
<OAI-PMH schemaLocation=http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd>
<responseDate>2018-01-15T18:32:15Z</responseDate>
<request identifier=oai:HAL:hal-01099211v1 verb=GetRecord metadataPrefix=oai_dc>http://api.archives-ouvertes.fr/oai/hal/</request>
<GetRecord>
<record>
<header>
<identifier>oai:HAL:hal-01099211v1</identifier>
<datestamp>2018-01-11</datestamp>
<setSpec>type:ART</setSpec>
<setSpec>subject:sde</setSpec>
<setSpec>subject:info</setSpec>
<setSpec>collection:SDE</setSpec>
<setSpec>collection:UNIV-CORSE</setSpec>
<setSpec>collection:UNIV-AG</setSpec>
<setSpec>collection:CNRS</setSpec>
<setSpec>collection:UNIV-REUNION</setSpec>
<setSpec>collection:SPE</setSpec>
<setSpec>collection:GIP-BE</setSpec>
<setSpec>collection:UNIV-CORSE-SPE</setSpec>
<setSpec>collection:PIMENT</setSpec>
</header>
<metadata><dc>
<publisher>HAL CCSD</publisher>
<title lang=en>A benchmarking of machine learning techniques for solar radiation forecastingin an insular context</title>
<creator>Lauret, Philippe</creator>
<creator>Voyant, Cyril</creator>
<creator>Soubdhan, Ted</creator>
<creator>David, Mathieu</creator>
<creator>Poggi, Philippe</creator>
<contributor>Physique et Ingénierie Mathématique pour l'Énergie, l'environnemeNt et le bâtimenT (PIMENT) ; Université de la Réunion (UR)</contributor>
<contributor>Sciences pour l'environnement (SPE) ; Université Pascal Paoli (UPP) - Centre National de la Recherche Scientifique (CNRS)</contributor>
<contributor>Laboratoire de Recherche en Géosciences et Énergies (LaRGE) ; Université des Antilles et de la Guyane (UAG)</contributor>
<contributor>Délégation Régionale Alpes - CNRS (MOY1100) ; Délégation Régionale Alpes - CNRS</contributor>
<description>International audience</description>
<source>ISSN: 0038-092X</source>
<source>EISSN: 1471-1257</source>
<source>Solar Energy</source>
<publisher>Elsevier</publisher>
<identifier>hal-01099211</identifier>
<identifier>https://hal.archives-ouvertes.fr/hal-01099211</identifier>
<identifier>https://hal.archives-ouvertes.fr/hal-01099211/document</identifier>
<identifier>https://hal.archives-ouvertes.fr/hal-01099211/file/Manuscript_Lauretetal_Rev_unmarked.pdf</identifier>
<source>https://hal.archives-ouvertes.fr/hal-01099211</source>
<source>Solar Energy, Elsevier, 2015, pp.00</source>
<language>en</language>
<subject lang=en>Intraday solar forecasting</subject>
<subject lang=en>machine learning techniques</subject>
<subject lang=en>statistical models</subject>
<subject>[SDE.IE] Environmental Sciences/Environmental Engineering</subject>
<subject>[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]</subject>
<type>info:eu-repo/semantics/article</type>
<type>Journal articles</type>
<description lang=en>In this paper, we propose a benchmarking of supervised machine learning techniques (neural networks, Gaussian processes and support vector machines) in order to forecast the Global Horizontal solar Irradiance (GHI). We also include in this benchmark a simple linear autoregressive (AR) model as well as two naive models based on persistence of the GHI and persistence of the clear sky index (denoted herein scaled persistence model). The models are calibrated and validatedwith data from three French islands: Corsica (41.91°N; 8.73°E), Guadeloupe (16.26°N; 61.51°W) and Reunion (21.34°S ; 55.49°E). The main findings of this work are, that for hour ahead solar forecasting,the machine learning techniques slightly improve the performances exhibited by the linear AR and the scaled persistence model. However, the improvement appears to be more pronounced in case of unstable sky conditions.These nonlinear techniques start to outperform their simple counterparts for forecasting horizons greater than one hour.</description>
<date>2015-01-02</date>
<rights>info:eu-repo/semantics/OpenAccess</rights>
</dc>
</metadata>
</record>
</GetRecord>
</OAI-PMH>
