基于协调学习的分布式协同抗干扰方法

Distributed Cooperative Anti-Jamming Method Based on Coordination Learning

针对强干扰和有限频谱资源的分布式信道接入场景,设计快速高效的动态信道接入方法,以实现有效的抗干扰通信性能。首先将干扰源信号设计为协调信号,从而将该分布式频谱接入问题构建为基于相关均衡(Correlated equilibrium,CE)的博弈模型。为有效解决不同干扰模式带来的收敛性能问题,设计了信号计数器(Event counters,ECs),根据干扰信号的特征对协调信号进行改进,构建了一种基于协调学习的分布式协同抗干扰方法,有效加速了CE点的生成。基于上述方案,设计了相应的基于协调信号优化的分布式信道接入抗干扰算法。仿真效果表明,所提方法能够有效完成分布式协同抗干扰及信道接入,实现更优的全网通信性能和公平性;在面对随机干扰时,能够在保证不丢失公平性的前提下实现更为快速有效的全网通信性能。

This paper investigates a fast and efficient dynamic channel access method for distributed channel access scenarios with strong jamming and limited channel resources to achieve effective anti⁃jamming communication performance.The proposed problem is constructed as a correlated equilibrium(CE)⁃based game model with jamming signals designed as coordination signals.To effectively raise the convergence performance under different jamming patterns,the event counters(ECs)are designed,where the coordination signal is improved according to the characteristics of the jamming signal.Next,a distributed cooperative anti⁃jamming approach is constructed based on coordinated learning,which effectively accelerates the generation of CE points.Based on the above approach,this paper designs a distributed channel access anti⁃jamming algorithm based on coordination signal optimization,and the simulation results show that the proposed approach can effectively achieve cooperative anti⁃jamming and channel access.Compared with the existing work,the proposed approach can achieve better communication performance and fairness in the face of sweep jamming.In the face of random jamming,it can achieve faster and better communication performance without losing fairness.