Please be advised that the site will be down for maintenance on Sunday, September 1, 2024, from 08:00 to 18:00, and again on Monday, September 2, 2024, from 08:00 to 09:00. We apologize for any inconvenience this may cause.
dc.contributor.author | Soubdhan, T.![]() |
|
dc.contributor.author | Voyant, C.![]() |
|
dc.contributor.author | Lauret, P.![]() |
|
dc.date.accessioned | 2015-08-25T06:28:44Z | |
dc.date.available | 2015-08-25T06:28:44Z | |
dc.date.issued | 2015 | |
dc.description.abstract | Paper presented to the 3rd Southern African Solar Energy Conference, South Africa, 11-13 May, 2015. | en_ZA |
dc.description.abstract | In this work, we have led an analysis of different global solar radiation forecasting models errors according to the global solar radiation variability. Different predictions models were performed such as 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 study a simple linear autoregressive (AR) model as well as two naïve models based on persistence of the GHI and persistence of the clear sky index (denoted herein scaled persistence model). The models are calibrated and tested with data from three French islands: Corsica (42.15°N ; 9.08°E), Guadeloupe (16.25°N ; 61.58°W) and Reunion (21.15°S ; 55.5°E). Guadeloupe and Reunion are located in a subtropical climatic zone whereas Corsica is in a tempered climatic zone hence, the global solar radiation variation differs significantly. The output error of the different models was quantified by the normalized root mean square error (nRSME). In order to quantify the influence of the global solar radiation variability on the forecasting models error we performed a classification of typical days. Each class of day is defined by a global solar radiation variability rate. For each class and for each location, forecasting models were performed and the error was quantified. With this analysis, global solar radiation forecasting models can be selected according to the location, the global solar radiation fluctuations and hence the meteorological conditions. | en_ZA |
dc.description.librarian | cf2015 | en_ZA |
dc.format.extent | 6 pages | en_ZA |
dc.format.medium | en_ZA | |
dc.identifier.citation | Soubdhan, T, Voyant, C & Lauret, P 2015, 'Influence of global solar radiation typical days on forecasting models error', Paper presented to the 3rd Southern African Solar Energy Conference, South Africa, 11-13 May, 2015. | en_ZA |
dc.identifier.uri | http://hdl.handle.net/2263/49474 | |
dc.language.iso | en | en_ZA |
dc.publisher | 3rd Southern African Solar Energy Conference, South Africa, 11-13 May, 2015. | en_ZA |
dc.rights | © 2015 University of Pretoria | en_ZA |
dc.subject | Global solar radiation | en_ZA |
dc.subject | Forecasting model errors | en_ZA |
dc.subject | Global horizontal solar irradiance | en_ZA |
dc.subject | Autoregressive process | en_ZA |
dc.subject | Neural network models | en_ZA |
dc.title | Influence of global solar radiation typical days on forecasting models error | en_ZA |
dc.type | Presentation | en_ZA |