基于改进麻雀搜索算法的虚拟机放置方法  

Virtual machine placement method based on improved sparrow search algorithm

作　　者：常盼 谢晓兰[1,2] CHANG Pan;XIE Xiao-lan(College of Information Science and Engineering,Guilin University of Technology,Guilin 541006,China;Guangxi Key Laboratory of Embedded Technology and Intelligent Systems,Guilin University of Technology,Guilin 541004,China)

机构地区：[1]桂林理工大学信息科学与工程学院,广西桂林541004 [2]桂林理工大学广西嵌入式技术与智能系统重点实验室,广西桂林541004

出　　处：《计算机工程与设计》2024年第11期3304-3311,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(62262011);广西自然科学基金项目(2021JJA170130)。

摘　　要：针对目前云数据中心存在资源利用率低、能源浪费严重的问题,提出一种基于改进麻雀搜索算法的虚拟机放置方法。针对基本麻雀搜索算法应用到虚拟机放置中存在易陷入局部最优、种群多样性不足等问题做出改进。在探索者位置更新后引入横纵交叉策略进行优化,改善算法在迭代前期就过早收敛于局部最优解的缺陷;将Levy飞行机制引入追随者位置更新中,扩大搜索范围,增加种群多样性;采用动态调节的透镜成像反向学习策略对种群个体求解反向解,增强种群逃离局部最优的能力。以降低能耗、资源浪费和SLA违背率为优化目标,采用基于模糊评估的方式对放置方案进行评价。实验结果显示,改进后的算法能减少资源浪费,提高服务质量,并且能显著降低能耗。Aiming at the problems of low resource utilization and significant energy waste in current cloud data centers,a virtual machine placement method based on an improved sparrow search algorithm was proposed.Improvements were made to address the problems that the basic sparrow search algorithm is prone to fall into local optimum and that of insufficient population diversity when applied to virtual machine placement.The crisscross strategy was introduced for optimization after the explorer position update to improve the defect that the algorithm converges to the local optimum solution too early in the first iteration.The Levy flight mechanism was introduced into the follower position update to expand the search range and increase the population diversity.A dynamically adjusted lens imaging reverse learning strategy was used to solve the reverse solution for the population individuals to enhance the ability of the population to escape from the local optimum.With the optimization objectives of reducing energy consumption,resource waste and SLA violation rate,the placement scheme was evaluated using a fuzzy evaluation-based approach.The experimental results show that the improved algorithm can reduce resource waste,enhance service quality,and significantly lower energy consumption.

关 键 词：虚拟机放置 麻雀搜索算法 模糊评估 横纵交叉策略 Levy飞行 透镜成像 仿真实验 

分 类 号：TP393.02[自动化与计算机技术—计算机应用技术]