A new neural network model for evaluating the performance of various hourly slope irradiation models: Implementation for the region of Athens

Mehleri, ED; Zervas, PL; Sarimveis, H; Palyvos, JA; Markatos, NC

dc.contributor.author	Mehleri, ED	en
dc.contributor.author	Zervas, PL	en
dc.contributor.author	Sarimveis, H	en
dc.contributor.author	Palyvos, JA	en
dc.contributor.author	Markatos, NC	en
dc.date.accessioned	2014-03-01T01:32:29Z
dc.date.available	2014-03-01T01:32:29Z
dc.date.issued	2010	en
dc.identifier.issn	0960-1481	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20154
dc.subject	Anisotropic models	en
dc.subject	Hourly slope irradiation models	en
dc.subject	Isotropic models	en
dc.subject	Radial basis function (RBF)	en
dc.subject.classification	Energy & Fuels	en
dc.subject.other	Anisotropic models	en
dc.subject.other	Coefficient of determination	en
dc.subject.other	Diffuse irradiance	en
dc.subject.other	Horizontal surfaces	en
dc.subject.other	Hourly slope irradiation models	en
dc.subject.other	Incidence angles	en
dc.subject.other	Inclined surface	en
dc.subject.other	Input datas	en
dc.subject.other	Isotropic models	en
dc.subject.other	Mean bias errors	en
dc.subject.other	Neural network model	en
dc.subject.other	Neural network techniques	en
dc.subject.other	Poor performance	en
dc.subject.other	Radial basis functions	en
dc.subject.other	Root mean square errors	en
dc.subject.other	Solar irradiances	en
dc.subject.other	Solar zenith angle	en
dc.subject.other	Statistical indices	en
dc.subject.other	Tilted planes	en
dc.subject.other	Tilted surface	en
dc.subject.other	Total solar irradiance	en
dc.subject.other	Anisotropy	en
dc.subject.other	Attitude control	en
dc.subject.other	Block codes	en
dc.subject.other	Irradiation	en
dc.subject.other	Mean square error	en
dc.subject.other	Radial basis function networks	en
dc.subject.other	Solar radiation	en
dc.subject.other	Neural networks	en
dc.subject.other	artificial neural network	en
dc.subject.other	diffusion	en
dc.subject.other	irradiation	en
dc.subject.other	isotropy	en
dc.subject.other	model test	en
dc.subject.other	numerical model	en
dc.subject.other	solar radiation	en
dc.subject.other	zenith angle	en
dc.subject.other	Athens [Attica]	en
dc.subject.other	Attica	en
dc.subject.other	Greece	en
dc.title	A new neural network model for evaluating the performance of various hourly slope irradiation models: Implementation for the region of Athens	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.renene.2009.11.005	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.renene.2009.11.005	en
heal.language	English	en
heal.publicationDate	2010	en
heal.abstract	The present study is divided into two parts. The first part deals with the comparison of various hourly slope irradiation models, found in the literature, and the selection of the most accurate for the region of Athens. In the second part the prediction of global solar irradiance on inclined surfaces is performed, based on neural network techniques. The models tested are classified as isotropic (Liu and Jordan, Koronakis, Jimenez and Castro, Badescu, Tian) and anisotropic (Bugler, Temps and Coulson, Klucher, Ma and Iqbal, Reindl) based on the treatment of diffuse irradiance. For the aforementioned models, a qualitative comparison, based on diagrams, was carried out, and several statistical indices were calculated (coefficient of determination R2, mean bias error MBE, relative mean bias error MBE/A(%), root mean square error RMSE, relative root mean square error RMSE/A(%),statistical index t-stat), in order to select the optimal. The isotropic models of ""Tian"" and ""Badescu"" show the best accordance to the recorded values. The anisotropic model of ""Ma&Iqbal"" and the pseudo-isotropic model of ""Jimenez&Castro"", show poor performance compared to other models. Finally, a neural network model is developed, which predicts the global solar irradiance on a tilted surface, using as input data the total solar irradiance on a horizontal surface, the extraterrestrial radiation, the solar zenith angle and the solar incidence angle on a tilted plane. The comparison with the aforementioned models has shown that the neural network model, predicts more realistically the total solar irradiance on a tilted surface, as it performs better in regions where the other models show underestimation or overestimation in their calculations. © 2009 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	Renewable Energy	en
dc.identifier.doi	10.1016/j.renene.2009.11.005	en
dc.identifier.isi	ISI:000276082900003	en
dc.identifier.volume	35	en
dc.identifier.issue	7	en
dc.identifier.spage	1357	en
dc.identifier.epage	1362	en