Publicación:
Optimal Estimation of Solar Radiation on Flat Surfaces for the Design of Energy Systems using Artificial Neural Networks
Optimal Estimation of Solar Radiation on Flat Surfaces for the Design of Energy Systems using Artificial Neural Networks
| dc.contributor.author | Huerta F.A.C. | es_PE |
| dc.contributor.author | Soldevilla F.R.C. | es_PE |
| dc.contributor.author | Delgado A. | es_PE |
| dc.contributor.author | Carbajal C. | es_PE |
| dc.date.accessioned | 2024-05-30T23:13:38Z | |
| dc.date.available | 2024-05-30T23:13:38Z | |
| dc.date.issued | 2019 | |
| dc.description | ACKNOWLEDGMENT Franklin Alfredo Cabezas Huerta would like to thank the support provided by the CER – UNI and also express special thanks to the National Fund for Scientific and Technological Development (FONDECYT – PERU) for the scholarship awarded to do PhD studies in Science with mention in Energetics in the National University of Engineering. | |
| dc.description.abstract | Solar energy systems use solar radiation to obtain useful energy, so to design and implement these systems anywhere on the surface of the earth it is very important to know the value of the incident solar radiation in the selected place. This radiation is usually obtained from meters such as pyranometers, pyrheliometers or actinographs from meteorological stations located near the place. As these instruments are expensive and usually have high measurement errors (5-9%), it is necessary to estimate the radiation in an optimal way. In this work, two mathematical methods are used to estimate the value of incident solar radiation on horizontal and tilted surfaces. The methods are: Method based on astronomical equations and method based on Artificial Neural Networks. The case study was conducted for the geographical location of the National University of Engineering (Lima, Peru). A database of meteorological variables measured for ten years and averaged every month was used to compare their measurements with the estimated results of the proposed mathematical methods. The results revealed that the estimated values of global solar radiation when applying the astronomical method differs on average 9% with respect to that provided by the database and 6% when applying Artificial Neural Networks. © 2019 IEEE. | |
| dc.description.sponsorship | Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - Concytec | |
| dc.identifier.doi | https://doi.org/10.1109/SHIRCON48091.2019.9024856 | |
| dc.identifier.scopus | 2-s2.0-85082388289 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12390/2297 | |
| dc.language.iso | eng | |
| dc.publisher | Institute of Electrical and Electronics Engineers Inc. | |
| dc.relation.ispartof | SHIRCON 2019 - 2019 IEEE Sciences and Humanities International Research Conference | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | solar radiation | |
| dc.subject | Artificial Neural Networks | es_PE |
| dc.subject | astronomical equations | es_PE |
| dc.subject | estimated values | es_PE |
| dc.subject | Solar energy systems | es_PE |
| dc.subject.ocde | http://purl.org/pe-repo/ocde/ford#2.02.04 | |
| dc.title | Optimal Estimation of Solar Radiation on Flat Surfaces for the Design of Energy Systems using Artificial Neural Networks | |
| dc.type | info:eu-repo/semantics/article | |
| dspace.entity.type | Publication |