区分服务中每跳行为的一种实现方案  

Implementation of Per Hop Behavior in Differentiated Service Architecture

作　　者：刘金梅[1] 王思明[1] 

机构地区：[1]广州暨南大学电子工程系,广东广州510632

出　　处：《计算机仿真》2005年第1期142-146,共5页Computer Simulation

摘　　要：区分服务体系结构 (简称DiffServ) ,作为一种互联网服务质量的解决方案 ,具有较好的可扩展性和健壮性。DiffServ中 ,其每跳行为 (PHB)的实现是关键。该文提出的PHB实现方案主要包括 :①采用类似最大队长和最小分配共享的DiffServ缓冲分配策略 ,进行队列间的缓冲区分配 ;②选用交错方式的RIOC策略进行队列管理 ;③使用一种新的调度算法———PRI/FWRR +,来进行队列调度。并通过计算机仿真说明 。The differentiated services architecture, i.e. DiffServ, is one of the solutions for Internet QoS because of its good scalability and robustness. Implementation of its per hop behavior(PHB) is quite essential. Our PHB implementation mainly contains three parts: a) A DiffServ buffer allocation scheme is used for the buffer allocation among different queues, based on a memory-sharing policy-sharing with maximum queue and minimum allocation; b) The RIOC with staggered-parameters is selected for queue management; C) A new two-level queuing mechanism is proposed for queue scheduling. Simulation tests indicate that the implementation of PHBs can satisfy the DiffServ requirements on network delay and link bandwidth allocation.

关 键 词：区分服务 每跳行为 服务质量 缓冲区分配 队列管理 队列调度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]