Dynamic link sleeping reconfigurations for green traffic engineering

Dynamic link sleeping reconfigurations for green traffic engineering
复制标题

DOI:
10.1002/dac.3224
复制
发表时间:
2017-06
影响因子:
2.1
通讯作者:
O. Okonor;Ning Wang;S. Georgoulas;Zhili Sun
O. Okonor;Ning Wang;S. Georgoulas;Zhili Sun
中科院分区:
计算机科学4区
文献类型:
--
作者:
O. Okonor;Ning Wang;S. Georgoulas;Zhili Sun

文献摘要

被引文献

相似文献

由于冗余网络设备上的大量能源浪费,高能耗已成为互联网界的一大担忧。一种有前途的节能方案是在流量需求较低时将网络元件重新配置为睡眠模式。然而,由于当今传统IP路由协议的性质,网络重新配置通常被认为是有害的,因为路由表重新收敛。为了使这些休眠网络元素(例如链路)对流量中断具有鲁棒性,我们提出了一种称为“指定休眠算法”的新型在线方案,旨在在节能期间删除网络链路而不造成流量中断。考虑到每日流量的性质,由于网络容量的减少,网络中可能会出现流量激增的情况。因此,我们提出了一种称为动态唤醒算法的补充方案,该算法可以智能地唤醒控制这种动态性所需的最少数量的休眠链路。这与恢复完整拓扑并牺牲节能或采用动态链路权重操作的正常范例相反。分别使用 GEANT 和 Abilene 网络的真实拓扑,我们表明所提出的方案可以节省大量能源而不影响网络性能。
The high volume of energy consumption has become a great concern to the Internet community because of high energy waste on redundant network devices. One promising scheme for energy savings is to reconfigure network elements to sleep mode when traffic demand is low. However, due to the nature of today's traditional IP routing protocols, network reconfiguration is generally deemed to be harmful because of routing table reconvergence. To make these sleeping network elements, such as links, robust to traffic disruption, we propose a novel online scheme called designate to sleep algorithm that aims to remove network links without causing traffic disruption during energy‐saving periods. Considering the nature of diurnal traffic, there could be traffic surge in the network because of reduced network capacity. We therefore propose a complementary scheme called dynamic wake‐up algorithm that intelligently wakes up minimum number of sleeping links needed to control such dynamicity. This is contrary to the normal paradigm of either reverting to full topology and sacrificing energy savings or employing on‐the‐fly link weight manipulation. Using the real topologies of GEANT and Abilene networks respectively, we show that the proposed schemes can save a substantial amount of energy without affecting network performance.