软件定义UAV网络的自适应QoS机制研究  

Research on Adaptive QoS Mechanism for Software Defined UAV Network

作　　者：吕鑫 黎海涛 黄嘉伟 LV Xin;LI Hai-tao;HUANG Jia-wei(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124

出　　处：《中国电子科学研究院学报》2023年第8期717-723,共7页Journal of China Academy of Electronics and Information Technology

基　　金：航空科学基金资助项目(2018ZC15003)。

摘　　要：针对软件定义无人机网络(SUNET)链路状态频繁变化难以保障用户服务质量(Quality of Service, QoS)的问题,本文研究了软件定义UAV网络中包含流量管控与队列调度的自适应QoS机制。首先,利用SUNET能够获取全局链路状态信息的优势,提出一种自适应QoS流量控制机制,其综合考虑链路带宽、不同类别消息的优先级和到期时间(ToE)等QoS要求,自适应调整OpenFlow交换机的数据流表项与计量表;然后,结合Linux流量控制的优先级(PRIO)和分层令牌桶(HTB)算法设计出多级队列调度方案以实现细粒度控制。仿真结果表明,所提自适应QoS机制能够显著降低高优先级消息的传输时延与丢包率,满足不同类型消息的差异化要求。To address the problem of frequent changes in the link state of software-defined UAV network(SUNET)that makes it difficult to guarantee Quality of Service(QoS),the adaptive QoS mechanism including the traffic control and queue scheduling algorithm of SUNET is investigated in this paper.First,taking advantage of SUNET's ability to obtain global link state information,an adaptive QoS flow control mechanism is proposed to adaptively adjust the data flow table entries and metering tables of the Open-Flow switch by taking into account QoS requirements such as link bandwidth,priority and time to expiry(ToE)of different categories of messages.Then,a multi-level queue scheduling scheme is designed to achieve fine-grained control by combining the priority of Linux flow control(PRIO)and hierarchical token bucket(HTB)algorithm.The simulation results show that the proposed adaptive QoS mechanism can significantly reduce the transmission delay and packet loss rate of high-priority messages and meet the differentiated requirements of different types of messages.

关 键 词：UAV网络 软件定义网络 QOS 队列调度 

分 类 号：TN92[电子电信—通信与信息系统]