一种高效的光分组交换网络缓存结构  

An Effective Buffering Architecture for Optical Packet Switching Networks

作　　者：王汝言[1] 张杰[1] 

机构地区：[1]重庆邮电大学光互联网及无线信息网络研究中心

出　　处：《半导体光电》2008年第1期93-97,共5页Semiconductor Optoelectronics

基　　金：国家“863”计划项目(2005AA122310);国家自然科学基金项目(90304004);教育部新世纪优秀人才支持计划项目(教技司[2005]2号,[2007]5号);重庆市科委项目(2005BB2062,2005AC2089);重庆市教委项目(KJ060508,KJ060513)

摘　　要：提出了一种新型的、用于光分组交换网络的光纤缓存结构。该结构针对光分组交换网络中解决输出端口竞争需要大量光纤延迟线,从而导致核心节点造价太高的缺陷,采用光纤分段式共享的机制,充分提高光纤延迟线的利用率。仿真和分析表明这种新型结构能有效降低丢包率,并可以取得令人满意的光分组平均延时参数;随着光纤延迟矩阵规模的增大,该结构仅需增加很少数目的光纤延迟线单元便可实现核心节点的扩展;在使用的总光纤延迟线单元数目上,该结构更能体现其优越性。A novel output buffer architecture for optical packet switching networks is proposed. The architecture which adopts fiber sharing mechanism and improves utilization of fiber delay lines, aims at solving the problem of requiring a large number of fiber delay lines which are used to solve resource contention but result in costliness in core node in optical packet switching networks. Simulation results and analysis show that the architecture can decrease packet loss probability effectively and achieve reasonable average delay per packet; when fiber delay matrix grows, the number of fiber delay lines will not grow obviously, this is favorable to extend of core node. At last, superiority of this architecture will be shown by comparing with simple output buffer architecture.

关 键 词：光分组交换 端口竞争 光纤延迟线 丢包率 平均延时 

分 类 号：TN929.11[电子电信—通信与信息系统]