Long-Term Solar Irradiance Forecasting Using Feed-Forward Back-Propagation Neural Network

Nowadays, it is widely acknowledged by power producers, utility companies and independent system operators that it is only through advanced forecasting, communications and control that renewable energy resources can collectively provide a firm, dispatchable generation capacity to the power systems. One of the challenges of realizing such a goal is the precise forecasting of solar irradiation, which is affected by latitude, terrain, season, time of day, and atmospheric conditions. Hence, this paper proposes a novel methodology for long-term solar radiation forecasting with hourly time intervals using feed-forward back-propagation time series artificial neural network. Simulation result proves that the proposed algorithm can offer highly features of compatibility and accuracy for solar predictions in comparison with actual solar radiation intensity reported by national solar radiation data base (NSRDB).

Long-Term Solar Irradiance Forecasting Using Feed-Forward Back-Propagation Neural Network Keywords:

Solar radiation forecasting , feed-forward back-propagation algorithm (FBPA) , time series artificial neural network (TS-ANN)