基于3次握手改进机制和SVM的无人机网络协作邻居发现协议  

A collaborative neighbor discovery protocol for unmanned aerial vehicle network based on improved three-way handshake mechanism and SVM

作　　者：王涛[1] 陈银豪 李平 吴雅婷[1] 孙彦赞[1] 王瑞[1] WANG Tao;CHEN Yinhao;LI Ping;WU Yating;SUN Yanzan;WANG Rui(School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China)

机构地区：[1]上海大学通信与信息工程学院,上海200444

出　　处：《上海大学学报（自然科学版）》2023年第1期82-94,共13页Journal of Shanghai University:Natural Science Edition

基　　金：国家自然科学基金资助项目(61671011,61771299)。

摘　　要：无人机在军事和民用领域都得到了广泛的应用,无人机的组网也成为研究热点之一.邻居发现作为组网完成的前提步骤,发挥着至关重要的作用.首先提出了基于3次握手改进机制的非协作邻居发现(3-handshake non-cooperation neighbor discovery,3-NCND)协议;然后融入支持向量机(support vector machine,SVM)算法,提出了基于3次握手改进机制和SVM的协作邻居发现(3-handshake and SVM cooperative neighbor discovery,3-SVMCND)协议,SVM作为分类器加入到邻居协议中,智能地将自身邻居节点信息发送给目标节点,减少了邻居节点推荐的数量,提高了邻居发现的速度.通过仿真实验比较了邻居发现时隙数、邻居发现率和能量消耗这3个性能指标.研究结果表明,相较于3-NCND协议,SVM-CND协议具有更快的发现速度和更高的邻居发现率.Unmanned aerial vehicles have been widely used in military and civil fields,and unmanned aerial vehicle networking has become a hot research topic.Neighbor discovery is a prerequisite step to complete a network.In this study,the 3-handshake non-cooperation neighbor discovery(3-NCND)protocol is first improved.Then a support vector machine(SVM)algorithm is integrated and a 3-handshake and SVM cooperative neighbor discovery(3-SVMCND)protocol is proposed.SVMs are trained as classifiers and then added to the neighbor discovery protocol.The protocol can intelligently recommend its own neighbor nodes to the target nodes and can reduce the number of neighbor node recommendations while improving the speed of neighbor discovery.In this study,three performance indices of neighbor discovery,namely,slot number,neighbor discovery rate,and energy consumption,are compared in a simulation experiment.Results show that 3-SVMCND has a faster discovery speed and higher neighbor discovery rate than those of 3-NCND.

关 键 词：无人机 支持向量机 二进制编码 协作邻居发现 智能 

分 类 号：TN915[电子电信—通信与信息系统]