Effects of Temperature and Pressure Information in a Hybrid (Fourier Series / Neural Networks) Solar Radiation Model

Abstract

Solar radiation modeling is a critical step in efficient management of solar energy. In this study, a novel solar radiation modeling procedure is developed with the a-priori information of temperature and pressure values, which are naturally dependent on solar radiation via indirect atmospheric phenomena. Firstly, daily behavior of hourly solar radiations is considered in frequency domain. Initial nine Fourier series coefficients are calculated for each day. Secondly, various neural networks models are built for prediction of these nine Fourier coefficients using the input data gathered from early morning hours and previous day. Apart from the solar radiation readings, temperature and pressure data are also used for developing a more accurate model. It is concluded that, the support of temperature and pressure data of the region improves the solar radiation model. Finally, differences between the performances of the proposed models reveal correlative relationships between atmospheric parameters and solar radiation.