...
首页> 外文期刊>IEEE systems journal >Tensor-Based Rule-Space Management System in SDN
【24h】

Tensor-Based Rule-Space Management System in SDN

机译:SDN中基于张量的规则空间管理系统

获取原文
获取原文并翻译 | 示例
           

摘要

This paper presents a tensor-based rule-space management (TERM) system for improving the available capacity of switches in software defined networking (SDN). Limited storage capacity of switches is a key challenge in SDN as the switches use ternary content addressable memories having very low capacity. Low rule storage capacity eventually leads to the high number of Packet-In messages and control plane overloading. The challenge is to design a dynamic scheme to store a large number of heterogeneous flow-rules in SDN switches and reduce the number of Packet-In messages. To address this problem, we apply the concept of tensor decomposition in order to aggregate flow-rules. In addition, we employ a rule caching mechanism for better throughput. Simulation results show the efficiency of TERM in terms of reduction in the number of Packet-In messages. TERM reduces the Packet-In message count by 57.78% than the flow aggregation approach proposed in the existing literature.
机译:本文提出了一种基于张量的规则空间管理(TERM)系统,用于提高软件定义网络(SDN)中交换机的可用容量。交换机的有限存储容量是SDN中的关键挑战,因为交换机使用容量非常低的三态内容可寻址存储器。低规则存储容量最终会导致大量Packet-In消息和控制平面过载。挑战在于设计一种动态方案以在SDN交换机中存储大量异构流规则,并减少Packet-In消息的数量。为了解决这个问题,我们应用了张量分解的概念来汇总流量规则。此外,我们采用规则缓存机制以提高吞吐量。仿真结果表明,在减少Packet-In消息数量方面,TERM的效率很高。与现有文献中提出的流聚合方法相比,TERM减少了Packet-In消息计数57.78%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 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