Artificial neural network models for predicting the solar radiation as input of a concentrating photovoltaic system

The energy production analysis of a system based on renewable technology depends on the inputs estimation accuracy. The solar energy is a free resource characterized by high variability; hence, its correct evaluation is a strategic factor for the feasibility of a solar system. In this paper a new methodological approach is presented in order to evaluate more accurately the electric and thermal energy production of a point-focus concentrating photovoltaic and thermal system (CPV/T). Two Artificial Neural Network (ANN) models for predicting solar global radiation and direct normal solar irradiance (DNI) are developed adopting different parameters such as climatic, astronomic and radiometric variables. In particular, a new combination of parameters is proposed in this paper and adopted first of all for the global radiation evaluation whose ANN model can be easily compared with the literature; the data are trained and tested by a multi layer perceptron (MLP). Hence, the results validation for the global solar radiation evaluation has encouraged to design an ANN model for the DNI by means of a similar variables set. The MLP network is trained, tested and validated for the hourly DNI estimation obtaining the MAPE, RMSE and R2 statistical indexes values respectively equal to 5.72%, 3.15% and 0.992. Finally, the electric and thermal outputs of a point-focus CPV/T system are evaluated varying the concentration factor and cells number, and adopting as input the DNI evaluation results obtained by the ANN model presented in this paper. The CPV/T system outputs are estimated referring to the city of Salerno (Italy) under different meteorological conditions.