Stochastic prediction of hourly global solar radiation for Patra, Greece

This paper describes the stochastic prediction of the hourly profile of the intensity of the global solar radiation, I(h; nj) for any day nj at a site. The prediction model requires one, two, or three morning measurements of the global solar radiation in a day nj, makes use of a rich data bank of past years recorded data, and provides I(h; nj) values for the rest hours of the day. The model is validated by comparing the I(h; nj) profiles generated for Patra, Greece, with the solar radiation measurements recorded for Winter, Autumn and Spring days, when solar radiation fluctuations often appear to be strong, while also comparing with the predicted by the METEONORM package I(h; nj) profile. Conclusions are deducted for the predictive power of the model. The proposed model, which is developed in MATLAB for the purpose of this research, provides I(h; nj) profile predictions very close to the measured values and offers itself as a promising tool for a predictive on-line daily load management.