Blind Source Separation for Forecast of Solar Irradiance

Abstract

The application of blind source separate (BSS) for forecasting the solar irradiance is presented. First, we used BSS method to separate the initial time sequence, and then we designed the best neural network topology. In consideration of the complex behavior of solar irradiance, either periodic or random, a kind of dynamic neural network, RBFN, was used for such case. After that the separating results were supplied to the input layer and were trained through adjusting the number of neurons in different layers and the weights and biases of the network. until the errors reached the stop conditions. Finally the forecasting model mentioned in this paper was tested through a practical sample, which indicates that the accuracy of the model is more satisfactory than without blind source separation. Thus the method proposed in this paper could also be applicable to other relating fields.