摘要
在SDN网络中,用户越来越注重业务的服务质量,对QoS业务数据流提出了多种服务质量目标要求。除了在流量控制算法上进行创新和改进之外,通过端口Enqueue排队动作来执行优化的缓存策略是一种有效提升服务质量的方法。应用排队论的经典M/M/1模型,通过统计数据包到达间隔的分布和处理时间的分布可以得到模型参数,从而计算出符合QoS目标要求的Enqueue行动的缓存队长等,优化了端口缓存资源的分配,提高了处理效率和吞吐量。
In SDN network,users pay more and more attention to the quality of service,and put forward multiple quality of service objectives for the data flow of QoS services.In addition to innovating and improving the traffic control algorithm,it is an ef⁃fective way to improve the quality of service to implement the optimized caching strategy through the port Enqueue queuing action.By using the classical M/M/1 model of queuing theory,the parameters of the model can be obtained through the distribution of arriv⁃al interval and processing time of statistical data packets,and the queue length of Enqueue actions that meet the requirements of QoS objectives can be calculated.The allocation of port cache resources is optimized,and the processing efficiency and throughput are improved.
作者
阳凯
林海涛
YANG Kai;LIN Haitao(College of Electronic Engineering,Naval University of Engineering,Wuhan 430033)
出处
《计算机与数字工程》
2021年第7期1426-1429,共4页
Computer & Digital Engineering
