电子学报 ›› 2016, Vol. 44 ›› Issue (3): 725-731.DOI: 10.3969/j.issn.0372-2112.2016.03.034

• 学术论文 • 上一篇    下一篇

虚拟网络映射高效节能运输模型及算法

陈晓华1,2, 李春芝1,3, 陈良育2, 曾振柄4, 蒋云良1   

  1. 1. 湖州师范学院信息工程学院, 浙江湖州 313000;
    2. 华东师范大学软件学院, 上海 200062;
    3. 华东师范大学计算机科学技术系, 上海 200241;
    4. 上海大学数学系, 上海 200444
  • 收稿日期:2014-07-23 修回日期:2014-11-10 出版日期:2016-03-25
    • 通讯作者:
    • 李春芝
    • 作者简介:
    • 陈晓华 男,1977年生于江西九江.湖州师范学院信息工程学院讲师,华东师范大学软件学院博士生.研究方向为下一代网络、云计算
    • 基金资助:
    • 国家自然科学基金 (No.61501184,No.61370173)

Transportation Model and Algorithms for Energy Efficient Virtual Network Embedding

CHEN Xiao-hua1,2, LI Chun-zhi1,3, CHEN Liang-yu2, ZENG Zhen-bing4, JIANG Yun-liang1   

  1. 1. School of Information and Engineering, Huzhou Teachers College, Huzhou, Zhejiang 313000, China;
    2. Software Engineering Institute, East China Normal University, Shanghai 200062, China;
    3. Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China;
    4. Department of Mathematics, Shanghai University, Shanghai 200444, China
  • Received:2014-07-23 Revised:2014-11-10 Online:2016-03-25 Published:2016-03-25

摘要:

网络虚拟化使得智能能量感知网络部署成为可能,已有研究忽略了节点映射能耗最优化.本文把节点映射能耗优化问题转化为生产地与销售地之间物资运输代价最优化问题,建立高效节能节点映射运输模型.根据最大元素法,提出了混合一阶段与两阶段映射算法,在链路映射的约束下找到节点分配最小能耗代价最优解;利用主动休眠策略,提出了基于运输模型的主动休眠虚拟网络映射节能算法;利用节点可重复映射技术,提出了基于运输模型的节点可重复映射算法,进一步提高了底层网络资源休眠数量.仿真结果验证了本文所提算法能够显著降低系统能耗,适合大规模高效节能虚拟网络映射.

关键词: 虚拟网络映射, 运输模型, 混合一阶段与两阶段算法, 高效节能

Abstract:

Network virtualization is an enabler for intelligent energy-aware network deployment.In the existing virtual network embedding algorithms,the minimization of energy consumption for mapping virtual nodes is ignored.In this paper,we create a transportation model for energy efficient virtual network embedding,in which energy consumption minimization for mapping virtual nodes is turned into the transportation model.An algorithm based on the largest element is proposed to obtain the optimization solution with node and link resource constraints,which is also a hybrid one-and-two stage algorithm.Besides,on the basis of the transportation model,we design an energy saving algorithm by use of the actively hibernating policy.If multiple virtual nodes in the same virtual network can be mapped to the same substrate node,a largest-element-and-transportation-model-based algorithm is proposed.These algorithms increase the number of substrate network hibernating resources.Simulation results show that the proposed algorithms can significantly reduce energy consumption.The theoretical analyses and the simulation results verify that our proposed algorithms suit energy efficient virtual network embedding for large scale substrate network.

Key words: virtual network embedding, transportation model, hybrid one-and-two stage algorithm, energy efficient

中图分类号: