基于改进卷积神经网络的频谱自适应通信传输  

Research on Adaptive Communication Based on Recognition on Improving Convolutional Neural Network

作　　者：张吉莹 石荣 李屹宽 胡柱 谢佳霖 ZHANG Ji-ying;SHI Rong;LI Yi-kuan;HU Zhu;XIE Jia-lin(National Key Laboratory Of Electromagnetic Space Security,Chengdu 610036,China;School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China)

机构地区：[1]电磁空间安全全国重点实验室,四川成都610036 [2]电子科技大学信息与通信工程学院,四川成都611731

出　　处：《中国电子科学研究院学报》2024年第5期432-441,共10页Journal of China Academy of Electronics and Information Technology

基　　金：国家自然科学基金重点资助项目(62231006);国家自然科学基金面上资助项目(62371093)。

摘　　要：虽然无线通信应用十分广泛,但是无线通信环境越来越复杂,很容易受到各种电磁干扰和电磁攻击的影响,提高其抗干扰性能一直是无线通信关注的重点。针对这一问题,利用认知无线电的电磁频谱感知结果,提出了一种基于改进卷积神经网络的频谱自适应通信传输方法。首先,利用传统的卷积神经网络和改进卷积神经网络对典型干扰类型进行识别,并根据识别结果估计对应的干扰参数,在此基础上结合频谱感知结果,遵循高效频谱利用效率原则自适应选取不受干扰影响的频谱来进行通信传输,以此达到抗干扰通信传输和提升频谱利用效率的双重目的。通过仿真验证了文中所提方法对干扰类型的识别正确率达到了98%以上,干扰参数估计的平均绝对百分比误差低于0.01,最后,利用软件无线电平台开展了实际的频谱自适应通信传输实验,在不同信干比下均能实现正常通信,实验结果表明其抗干扰通信效果显著。Although wireless communication is widely used,the wireless communication environment is becoming more and more complex,and it is easily affected by various electromagnetic interference and electromagnetic attack.Improving its anti-interference performance has always been the focus of wireless communication.To solve this problem,a spectrum adaptive communication transmission method based on improving convolutional neural network is proposed by using the results of electromagnetic spectrum sensing of cognitive radio.Firstly,the traditional convolutional neural network and the improved convolutional neural network are used to identify the typical interference types,and the corresponding interference parameters are estimated according to the identification results.On this basis,combined with the spectrum sensing results,the spectrum that is not affected by interference is adaptively selected for communication transmission according to the principle of efficient spectrum utilization efficiency,so as to achieve the dual purpose of anti-interference communication transmission and improving spectrum utilization efficiency.The simulation results show that the recognition accuracy of the proposed method for interference types is more than 98%,and the mean absolute percentage error of interference parameter estimation is less than 0.01.Finally,the actual spectrum adaptive communication transmission experiment is carried out on the software radio platform,and the normal communication can be achieved under different signal to interfer-ence ratios.The experimental results show that the anti-interference communication effect is remarkable.

关 键 词：改进卷积神经网络 干扰识别 参数估计 自适应抗干扰传输 频谱利用效率 

分 类 号：TN97[电子电信—信号与信息处理]