基于帧抢占感知的动态流量疏导策略
首发时间:2021-04-14
摘要:Ethernet-over-WDM网络中IP业务被封装成以太网帧的方式进行传输,数据帧在队列中存储转发会产生排队时延,对时延敏感业务产生影响。帧抢占技术允许高优先级帧抢占低优先级帧的发送端口,减少其排队时延。流量疏导将多个业务流聚合到一个波长上进行传输,将帧抢占技术应用到流量疏导过程中,可以在多业务竞争同一端口时减少时延敏感业务的排队时延。然后由于成本限制,网络中的节点不可能全部部署帧抢占功能,不具有抢占功能的节点无法对被抢占后的帧进行重组,影响数据帧的正常传输。针对节点帧抢占功能受限的问题,本文提出一种基于帧抢占感知的流量疏导辅助图模型,并且根据辅助图模型设计了动态流量疏导策略。仿真结果表明,不同的疏导策略在不同网络资源配置下性能表现不同,辅助图模型有助于选择帧抢占限制条件下的最佳路径。
关键词: Ethernet-over-WDM 动态流量疏导 帧抢占技术 辅助图模型?????
For information in English, please click here
Dynamic Traffic Grooming Policy for Frame Preemption Sensing
Abstract:In the Ethernet-over-WDM network, IP services are encapsulated into Ethernet frames for transmission. The storage and forwarding of data frames in the queue will produce queuing delay, which will affect the latency-sensitive services.Frame preemption technology allows high-priority frames to preempt the sending port of low-priority frames, reducing its queuing delay.Traffic grooming aggregates multiple service flows to one wavelength for transmission, and this paper applies frame preemption technology to the traffic grooming process.It can reduce the queuing delay of latency-sensitive services when multiple services compete for the same port.However, due to cost constraints, it is impossible for all nodes in the network to deploy the frame preemption function, and nodes that do not have the preemption function cannot reassemble the preempted frames, which affects the normal transmission of data frames.Aiming at the problem of limited frame preemption function of nodes, this paper proposes a traffic grooming auxiliary graph model based on frame preemption sensing, and designs a dynamic traffic grooming strategy according to the auxiliary graph model. The simulation results show that different grooming policies have various performance under different network configurations. The auxiliary graph model helps to choose the best path under the frame preemption constraints.
Keywords: Ethernet-over-WDM dynamic traffic grooming fronthaul frame preemption technology auxiliary graph model?????
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于帧抢占感知的动态流量疏导策略
评论
全部评论0/1000