云计算中基于Shapley值改进遗传算法的虚拟机调度模型

云计算系统具有服务器规模大、用户范围广的特点，但同时也消耗了大量的能源，导致云供应商的高运营成本和高碳排放等问题。云计算高度虚拟化，如何分配和管理其虚拟资源，从而保证高效的物理资源利用和能耗控制，是一个多参数博弈过程，同时也是该领域的一个研究热点。提出了一种虚拟机调度模型及基于Shapley 值的遗传算法（SV-GA），可通过经济学概念Shapley 值计算出参与工作的物理机贡献值，并通过该贡献值修正遗传算法中变异步骤的概率参数，从而完成虚拟机调度的任务。实验结果表明，与Max-Min、LrMmt及DE算法相比，SV-GA在虚拟机调度过程中的迁移时间、次数、SLA违背率、能耗等多参数博弈中具有优异的表现。

Virtual machine scheduling model based on Shapley value modified genetic algorithm in cloud computing

Cloud computing system has the characteristics of large-scale servers and a wide range of users.However, it also consumes a huge number of energy, resulting in high operating costs of cloud providers and high carbon emissions issue.Cloud computing is highly virtualized.How to allocate and manage the virtual resources to ensure efficient physical resource utilization and energy consumption control is a multi-parameter game problem, and it is also a research hotspot in this field.A virtual machine scheduling model and the corresponding SV-GA were proposed, which could calculate the contribution value of the physical machine participating in the work through the Shapley value, and modify the probability parameter of the mutation step in the genetic algorithm through the contribution value, so as to complete the task of virtual machine scheduling.The experimental results show that during the comparison with Max-Min, LrMmt and DE, the SV-GA shows its excellent performance in the multi-parameter game including migration time, times, SLA violation rate and energy consumption in the virtual machine scheduling process.