基于萤火虫算法的虚拟机部署能效优化策略  

Virtual machine placement energy-efficient optimization based on glowworm swarm optimization algorithm

作　　者：龚婷婷 徐健锐[1,2] GONG Ting-ting;XU Jian-rui(School of Computer Science and Telecommunication Engineering,Jiangsu University,Zhenjiang 212013,China;Zhenjiang Branch,Jiangsu Union Technical Institute,Zhenjiang 212016,China)

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013 [2]江苏联合职业技术学院镇江分院,江苏镇江212016

出　　处：《计算机工程与设计》2019年第7期1896-1902,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(61302124);江苏省高校自然科学研究面上基金项目(16KJB520010)

摘　　要：综合考虑数据中心能耗、应用SLA违例及虚拟机迁移量的均衡优化,提出一种基于萤火虫算法的虚拟机部署优化策略。建立虚拟机部署优化的目标函数与约束条件,利用装箱思想对虚拟机部署进行抽象,设计基于萤火虫算法的虚拟机部署优化方法,通过萤火虫种群初始化、萤光素更新、萤火虫移动以及局部半径范围更新4个阶段的最优解搜索过程,实现虚拟机部署能效优化。实验结果表明,该算法可以通过虚拟机重部署实现数据中心能耗与性能的均衡优化。For considering synthetically the trade-off optimization of the energy consumption in data center,SLA violation of applications and the number of virtual machine migration,a virtual machine placement optimization strategy based on glowworm swarm optimization algorithm was presented. The objective function and the corresponding constraints of the virtual machine placement were established. The bin-packing idea was used to abstract the virtual machine placement problem. A virtual machine placement optimization method based on glowworm swarm optimization algorithm was designed. A four-stage optimal searching process was used,including the population initialization of glowworm swarm,updating the luciferin,the movement of glowworm and updating the local radius range,to complete the optimal virtual machine placement. Experimental results show that the proposed algorithm can trade-off the energy consumption of data center and the performance of applications by the re-placement of virtual machines.

关 键 词：数据中心 虚拟机部署 萤火虫算法 能耗 服务等级协议 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]