Research On Intelligent Spectrum Sensing Strategy Of Dynamic Time-Varying Channel In Space TT&C Network

With the advancement of science and technology,mankind has made more and more in-depth explorations in the aerospace field.In order to further improve the utilization of spectrum resources of the aerospace measurement and control system,this thesis studies the intelligent spectrum sensing strategy under the dynamic time-varying channel of the aerospace measurement and control network,and proposes an intelligent improvement method in the single-user and multi-user spectrum sensing scenarios.Improve the overall cognition level of aerospace measurement and control system.This thesis first studies the single-user local spectrum sensing algorithm and verifies its sensing performance under different SNR ratios.Secondly,in response to the problem of noise uncertainty,an improved perception strategy based on recurrent neural network for channel noise recognition is proposed.By learning channel data,it provides noise prior data for single-user local perception,which improves the generalization ability of single user’s spectrum perception under different noise channels.At the same time,for the noise intensity estimation technology,an enhanced perception method based on generative adversarial network is proposed,which can learn the mean square error characteristics of channel noise under a small sample data set,and can also improve the accuracy of the recurrent neural network channel recognition method.Finally,in order to improve the sensing ability of low SNR users,this thesis proposes a distance based multi-level group cooperative sensing strategy combined with the idea of recursion.According to the distance between the sensing users and the authorized users,the strategy divides the cooperation groups hierarchically,which can not only improve the detection probability of low SNR users,but also guarantee the detection performance of the whole cooperative sensing system.Through simulation,it is verified that the method proposed in this thesis can effectively shorten the detection inaccuracy interval caused by the uncertainty of noise,which has a certain helping effect on improving the spectrum sensing ability of space TT&C system,and has practical significance for the development of space TT&C technology.