首页> 外文会议>IEEE Conference on Computer Communications Workshops (INFOCOM 2010) >Adaptive Re-Routing over Circuits: An Architecture for an Optical Backbone Network
【24h】

Adaptive Re-Routing over Circuits: An Architecture for an Optical Backbone Network

机译:电路上的自适应重路由:光骨干网的架构

获取原文
获取原文并翻译 | 示例

摘要

As Internet traffic continues to grow unabated at an exponential rate, it is unclear whether the existing packet routing network architecture based on electronic routers will continue to scale at the necessary pace. On the other hand, optical fiber and switching elements have demonstrated an abundance of capacity that appears to be unmatched by electronic routers. Although a number of optical backbone architectures have been proposed (e.g., optical burst switching), they generally rely on frequent dynamic circuit reconfigurations and new signaling protocols for network-wide coordination. Recently, we proposed an alternative optical backbone architecture called COPLAR based on a paradigm of coarse optical circuit switching by default and adaptive re-routing over circuits when necessary [4]. This approach is based on the provisioning of long-duration quasi-static optical circuits between IE (Ingress-Egress) router pairs at the boundary of the network to carry the traffic by default. When a provisioned circuit is inadequate, we adaptively load-balance the excess traffic across circuits with spare capacity so that all traffic can be routed to their final destinations without the need to create new circuits on-the-fly. Our initial work was focused on the system architecture design and the provisioning of quasi-static circuits. In this paper, we focus on the problem of adaptive re-routing over circuits. Our evaluation using real traffic data on two real backbone networks (Abilene and GEANT) shows that our adaptive re-routing over circuits approach can effectively accommodate excess traffic even under heavy traffic loads.
机译:随着Internet流量继续以指数级的速度增长,目前尚不清楚基于电子路由器的现有分组路由网络体系结构是否会继续以必要的速度扩展。另一方面,光纤和交换元件已显示出大量容量,这似乎是电子路由器无法比拟的。尽管已经提出了许多光骨干架构(例如光突发交换),但是它们通常依靠频繁的动态电路重新配置和新的信令协议来进行全网协调。最近,我们提出了一种可选的光骨干架构,称为COPLAR,它基于默认情况下的粗略光路切换和必要时对电路进行自适应重新路由的范例[4]。此方法基于在网络边界的IE(入口-出口)路由器对之间提供长时间的准静态光路,以默认情况下承载流量。当预配置的电路不足时,我们会以备用容量自适应地平衡电路之间多余的流量,以便所有流量都可以路由到其最终目的地,而无需即时创建新电路。我们的最初工作集中于系统架构设计和准静态电路的配置。在本文中,我们关注于电路上的自适应重路由问题。我们使用两个真实骨干网(Abilene和GEANT)上的真实流量数据进行评估,结果表明,即使在繁重的流量负载下,我们的自适应电路重路由方法也可以有效地容纳过量流量。

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