首页> 中文期刊> 《电子与信息学报》 >面向可重构服务承载网的分域混合承载组调度研究

面向可重构服务承载网的分域混合承载组调度研究

         

摘要

传统网络技术体系,网络是封闭的、刚性的,无法满足未来网络大量差异化业务的规模化应用,由此提出了面向服务提供的柔性网络技术体系,该体系将传统网络中的用户业务、网络服务和网络基础设施中的紧耦合关系转变为松耦合关系,通过资源分割构建可重构服务承载网实现对业务的服务质量保证.该文分析了服务承载网映射到交换结构的需求,提出分域调度的思想.通过选择关闭部分交叉节点的方法建立了crossbar交换结构分域模型,实现了分域调度的端口分离.提出了支持可重构服务承载网构建的混合承载组调度(HCGS)算法,推导了承载组内SDRR(Smoothed Deficit Round Robin)调度、单个域内基于时间戳的输入端口调度和交叉节点输出端口调度算法,证明了HCGS具有良好的时延性能和最坏公平指数(WFI)公平性.仿真结果表明:在均匀分布的泊松业务源条件下,分域HCGS算法具有更优的时延性能,可保证业务带宽的公平性.在diagonal非均匀允许流量条件下,该算法的吞吐量可达100%.%Network is rigid and close in the traditional technology system, which is not meeting intending abundant different business of scale application. So flexible network technology system facing on service providing is proposed, which change traditional close coupling connection of client business, network service and network foundation facilities to loose coupling connection. Then it can guarantee Quality of Service (QoS) by constituting Reconfigurable Service Carrying Network (RSCN) based on network resource slices. On above technology background, this paper proposes the idea of partition domain schedule after analyzing the requirement of switching fabric from mapping result of RSCN. It constructs crossbar switching resource slicing model by selecting closing part crossbar switching point. It proposes Hybrid Carrying Group Scheduling (HCGS) algorithm. And deduces Smoothed Deficit Round-Robin (SDRR) in the carrying group, input port scheduling algorithm based on timestamp in one carrying domain and output port scheduling algorithm of crossbar switching point. And proves that HCGS algorithm has better time delay and Worst-case Fairness Index (WFI) fairness performance. Then it uses SPES to realize emulation of HCGS algorithm, the result of emulation is that partition domain HCGS algorithm has optimizing time delay and traffic bandwidth fairness performance based on uniform Poisson traffic source, and has 100% throughput based on non-uniform diagonal admissible traffic source.

著录项

相似文献

  • 中文文献
  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号