Abstract: It is significant to solar energy related industries predicting solar radiation accurately, for the volatility and intermittent of solar radiation, a solar radiation prediction method based on the Optimization wavelet neural network with curve fitting and Pauta criterion is put forward. Predicting the solar radiation amount through the historical solar radiation data and meteorological data, fitting curve to the measured value, and get rid of the great error of the fitting value and the measured value according to the Pauta criterion. The correctional data is used as the input of the wavelet neural network, to avoid problem of measuring information malformation because of input with the extreme data. Additional test data to do the optimization calculation of hidden layer node number for wavelet neural network to overcome the shortcoming that Wavelet Neural Network cannot determine the number of hidden layer nodes. By comparing different prediction models, the correctness of the proposed algorithm and model is verified.