Methods for Site-Adaptation of Satellite-Based DNI Time Series: Application to Brazilian Northeast
Abstract
The standard procedure today in solar industry is the acceptance of solar irradiance estimates via satellite images (normally time series longer than 15 years) and its adaptation to the site where the solar power plant will be. The adaptation is performed correlating the long time series via satellite with a short time series (1 year) of good quality (first class pyroheliometers and standard secondary pyranometer), measured on terrestrial surface. The purpose of this work was the development as well as the demonstration of four computational techniques (simple regression, multiple regression, ANN-MLP and ANN-SVM) which allowed the correction of this bias. The estimators developed were applied for Patos, city located in the Northeast Brazil. The application of such approaches resulted not only in expressive decrease of the bias but also, when it comes to SVM, in significant reduction of the mean square deviation of the originally estimated values via satellite image.