Artificial neural networks for the generation of direct normal solar annual irradiance synthetic series

Abstract

The use of concentrators implies that CPV systems only work with the Direct Normal Irradiance (DNI). So it is necessary to know DNI data in order to estimate the energy that will be produced by the system, perform economic analysis, supervise plant operation, etc. However, DNI Typical Meteorological Year datasets are expensive and rarely available due to the cost and sophistication of measurement devices and data processing requirements. Particularly, there is a lack of data on the Sunbelt countries, which are more favorable for the use of CPV. In this work, an artificial neural network is used for the generation of DNI hourly time series for some Spanish locations. The model was trained and tested with different locations and different year's data. Although several authors have proposed different methods for the generation of solar radiation synthetic series, these methods are for global radiation and flat panel, nevertheless, we calculate them for direct normal solar radiation and used for CPV systems. A Multilayer Perceptron is explained, looking over the first rudimentary initial version and the last more elaborated final version. Finally, an application of this methodology is presented.