Short term photovoltaic power generation forecasting using RBF neural network

The short-term photovoltaic power generation forecasting is of great significance for the power system and energy management system(EMS). In this paper, the short-term forecasting model of PV generation power based on the RBF neural network is proposed, which forecast the power of PV generation system for the next 24 hours. Factors of position, environment, and inner performance of the system are fully considered. A novel prediction strategy combined with mechanism model is used, and modulations of parameters are executed according to online training of neural network. Experimental results prove that the proposed model reduces the deviation between the predict power and the actual power significantly, and can achieve fast and accurate prediction even the amount of number is very small.