Publication
Modelos para la predicción del autoconsumo en sistemas fotovoltaicos conectados a red
| dc.contributor.author | López, Llanos Mora | |
| dc.contributor.author | Sidrach-de-Cardona, Mariano | |
| dc.date.accessioned | 2020-11-18T18:16:15Z | |
| dc.date.available | 2020-11-18T18:16:15Z | |
| dc.date.issued | 2020-11 | |
| dc.description | CIES2020 - XVII Congresso Ibérico e XIII Congresso Ibero-americano de Energia Solar | pt_PT |
| dc.description.abstract | RESUMEN: En este trabajo se presentan los resultados obtenidos para la modelización y optimización de instalaciones fotovoltaicas de autoconsumo. Se han obtenido las curvas de autoconsumo y autosuficiencia para diferentes perfiles de consumo horario en función de la potencia pico instalada y el tamaño de la batería. El estudio se ha realizado para tres ciudades españolas con diferentes condiciones climáticas. Para la generalización de los resultados se proponen diferentes modelos de aprendizaje automático que permiten estimar estos parámetros. Las variables de entrada de estos modelos están relacionadas con la configuración de la instalación, su ubicación y el tipo de perfil de consumo. El modelo que arroja mejores predicciones en el parámetro de autosuficiencia es Random Forest, que en la validación cruzada tiene un error relativo del 5%. Para la predicción del autoconsumo, el modelo que mejor se comporta es el Perceptrón Multicapa, con un error absoluto promedio de 0.55 y un error relativo del 3%. | pt_PT |
| dc.description.abstract | ABSTRACT: The results obtained for the modeling and optimization of photovoltaic self-consumption facilities are presented. The study has been carried out for three Spanish cities with different climatic conditions. The self-consumption and self-sufficiency curves for different hourly consumption profiles have been obtained based on the installed peak power and the size of the battery. In order to generalize the obtained results, different models of machine learning are proposed to estimate these parameters. The input variables of these models are related to the configuration of the installation, its location and the type of consumption profile. The model with best predictions of self-sufficiency is Random Forest, which in cross-validation has a relative error of 5%. For the prediction of self-consumption, the model that performs best is the Multilayer Perceptron, with an average absolute error of 0.55 and a relative error of 3%. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.citation | López, Llanos M... [et.al.] - Modelos para la predicción del autoconsumo en sistemas fotovoltaicos conectados a red. In: CIES2020: As Energias Renováveis na Transição Energética: Livro de Comunicações do XVII Congresso Ibérico e XIII Congresso Ibero-americano de Energia Solar. Helder Gonçalves, Manuel Romero (Ed.). Lisboa, Portugal: LNEG, 3-5 Novembro, 2020, p. 545-552 | pt_PT |
| dc.identifier.doi | 10.34637/cies2020.1.2065 | pt_PT |
| dc.identifier.isbn | 978-989-675-076-3 | |
| dc.identifier.uri | http://hdl.handle.net/10400.9/3402 | |
| dc.language.iso | spa | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | LNEG - Laboratório Nacional de Energia e Geologia | pt_PT |
| dc.relation.publisherversion | https://doi.org/10.34637/cies2020.1.2065 | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Solar energy | pt_PT |
| dc.subject | Photovoltaic systems | pt_PT |
| dc.subject | Self-consumption | pt_PT |
| dc.subject | Evaluation | pt_PT |
| dc.subject | Modelling | pt_PT |
| dc.title | Modelos para la predicción del autoconsumo en sistemas fotovoltaicos conectados a red | pt_PT |
| dc.type | conference object | |
| dspace.entity.type | Publication | |
| oaire.citation.conferencePlace | Lisboa, Portugal | pt_PT |
| oaire.citation.endPage | 552 | pt_PT |
| oaire.citation.startPage | 545 | pt_PT |
| oaire.citation.title | CIES2020 - XVII Congresso Ibérico e XIII Congresso Ibero-americano de Energia Solar | pt_PT |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | conferenceObject | pt_PT |
Files
Original bundle
1 - 1 of 1