基于中心度寻核的能效优化虚拟网映射算法  

Energy efficient virtual network embedding based on searching network centrality kernel

作　　者：王博[1] 陈庶樵[1] 王志明[1] 王文钊[1] 

机构地区：[1]国家数字交换系统工程技术研究中心,郑州450002

出　　处：《计算机应用研究》2015年第7期2087-2091,共5页Application Research of Computers

基　　金：国家"973"计划资助项目(2012CB315901)

摘　　要：虚拟网映射是网络虚拟化技术的关键问题,以往研究常关注供应商的收益与开销,而网络设备的大量能源浪费使得供应商开始关注节能。将紧密中心度概念引入虚拟网映射问题中,同时考虑节点的位置和能力,优先使用已工作节点和缩短链路长度来降低能耗,提出了一种寻找核心节点优先映射(寻核)算法。该算法通过检验确保所选底层核心节点满足虚拟核心节点要求,节点和链路映射同步进行,同时根据贪婪策略保证所选底层网络节点跳数较小。仿真实验结果表明,该算法能够提高映射接收率约10%、改善收益开销比和收益能耗比10%以上。Virtual network embedding !s the key issue of the network virtualization technology, previous studies often focus on the benefits of the providers, and numerous waste of energy in network infrastructures has stimulated the interest on energy consumption reduction by providers. This paper introduced network closeness centrality to the virtual network embedding, simultaneously considering the location and capacity of the node. It presented one algorithm which searched the kernel node and embedded it prior （searching kernel）, using the active node in preference and shortening length of the substrate links to reduce energy consumption. The algorithm Checked and ensured that the selected substrate kernel node met requirements of the virtual kernel node, together embedded nodes and links based on greedy strategy to ensure the shorter distance between the nodes in the selected substrate network. The simulation results demonstrate the proposed algorithm increases accept ratio about 10%, and improves revenue cost rate and revenue energy rate more than 10%.

关 键 词：虚拟网映射 能效优化 资源整合 紧密中心度 寻核 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]