Non-Gaussian Noise Cooperative Spectrum Sensing Scheme Based on Rao Test

This paper studies the problem of spectrum detecting in cognitive user under the condition of non-Gauss noise, fitting of non-Gaussian noise background in the mixed-Gaussian model, and using the method of moment estimation to estimate the mixed-Gaussian model parameters such as mixing coefficient. Base on this, the mixed-Gaussian Rao test method is applied to detect spectrum in cognitive users, derivation mixed-Gaussian Rao test of the test statistic and detection performance formula, analysis and comparison the detection performance between the mixed-Gaussian Rao and Gaussian Rao. Through theoretical analysis and Monte Carlo simulation shows the fact that in the case of the probability of false alarm is certain, Rao test method based on mixed-Gaussian can effectively improve the non-Gaussian noise detection performance in cognitive radio networks users.