Abstract:

Photovoltaic Array is nonlinear, and the power generated by it is influenced by sun light, temperature and so on. We put forward PV array model by using neural networks identification technique in this paper. The temperature, radiation and voltage of the solar cells are taken as the input and the current as the output of the neural networks model. Using RBF neural network to model for photovoltaic battery and particle swarm optimization algorithm to optimize the RBF neural network, finally the photovoltaic model is established. Simulated experiments are carried out on the photovoltaic battery data, the results show that the improved RBF neural networks have better accuracy and adapt ability than traditional RBF method. The RBF neural networks modeling makes it possible to design on-line controller of photovoltaic system.

Key words: photovoltaic array；particle swarm optimization；neural network；simulation