利用蚁群算法完成虚拟机放置的优化  

ACO-VMP:Using ant colony optimization algorithm for virtual machine placement

作　　者：陈艳 周天绮 徐胜超 CHEN Yan;ZHOU Tian-qi;XU Sheng-chao(School of Computer Science and Engineering,Guilin University of Aerospace Technology,Guilin 541004,China;School of Medical Instruments,Zhejiang Pharmaceutical College,Ningbo 315100,China;School of Electronic and Information Engineering,Beibu Gulf University,Qinzhou 535011,China)

机构地区：[1]桂林航天工业学院计算机科学与工程学院,广西桂林541004 [2]浙江医药高等专科学校医疗器械学院,浙江宁波315100 [3]北部湾大学电子与信息工程学院,广西钦州535011

出　　处：《计算机工程与设计》2021年第5期1229-1234,共6页Computer Engineering and Design

基　　金：国家自然科学基金重点基金项目(60433040);国家自然科学基金项目(50577027);广西自然科学基金项目(2016GXNSFAA380226);广西高校中青年教师基础能力提升基金项目(2018KY0651、2018KY0659);桂林航天工业学院电子信息重点学科及物联网与大数据应用研究中心资助基金项目(KJPT201801)。

摘　　要：提出利用蚁群算法来完成虚拟机放置过程的优化策略(ant colony optimization based virtual machine placement,ACO-VMP)。建立基于向量代数的物理服务器多维资源的描述,以云数据中心的整体能量消耗降低和活动物理主机数量减少为目标函数;蚁群算法中信息素增强变量的更新与所有虚拟机-物理主机的映射密切相关,且每次都考虑物理主机的多维资源的平衡利用。Cloudsim模拟器仿真结果表明,虚拟机的装箱效率明显提高,活动物理主机数量和能量消耗减少比其它放置策略明显减少。An ant algorithm for virtual machine placement called ACO-VMP was proposed.A vector algebra-based complementary resource utilization capturing technique was used and multi-dimensional resource demands were described.The active virtual machines were packed in the minimum number of physical servers considering multi-dimensional resource demands with the goal of energy saving and maximization of server resource utilization in data centers.Pheromone levels were also associated to all VM-to-PM assignments and heuristic values were computed dynamically for each VM-to-PM assignment in favor of both overall and balanced resource utilization of the host.Experimental results and performance analysis show that the strategy leads to a further improvement in packing efficiency compared with the old optimized algorithm strategies.The active host number and energy consumption are also reduced.

关 键 词：蚁群算法 多维物理资源 负载均衡 虚拟机放置 资源利用效率 

分 类 号：TP393.2[自动化与计算机技术—计算机应用技术]