摘要
以云用户QoE为研究目标,提出一种在云系统中可根据物理资源性能的差异性对云业务进行适应性划分的动态切割算法。该算法结合可用资源的实际约束条件建立云业务切割数学模型。在此模型下以最小化云业务处理时延代价为目标函数,为切割过程引入权重机制和可切割粒度等适应性因数计算出科学的动态切割系数,进而为云系统中不同规模的云业务生成一个动态的切割方案集合。所构思的云业务切割算法经测试表明了其相对于传统的研究不仅表现出了一定的优越性,同时该算法对于切割过程的科学考量也进一步增强了算法的动态适应性。
Taking cloud user QoE as the research goal,a dynamic cutting algorithm is proposed,which can conduct the adaptive partition of cloud services according to the difference of physical resource performance in cloud system.The algorithm combines the actual constraints of available resources to establish a mathematical model of cloud business cutting.In this model,the objective function is to minimize the delay cost of cloud service processing.The adaptive factors such as weight mechanism and cuttable granularity are introduced into the cutting process to calculate the scientific dynamic cutting coefficient,and then a dynamic cutting scheme set is generated for different scale cloud services in the cloud system.The cloud service cutting algorithm proposed in this paper has been tested and proved to be superior to the traditional research.At the same time,the scientific consideration of the algorithm for cutting process also further enhances the dynamic adaptability of the algorithm.
作者
郑小兰
ZHENG Xiao-lan(Engineering College,Fuzhou Institute of Technology,Fuzhou Fujian,350506)
出处
《山西大同大学学报（自然科学版）》
2020年第6期42-45,共4页
Journal of Shanxi Datong University(Natural Science Edition)
基金
福建省中青年教师教育科研项目[JAT191016]
福州市市级科技计划项目[2019-SG-15]
福州理工学院高等教育教学改革研究项目[LGJG2019028]。
关键词
云业务
切割
计算
时延
开销
cloud service
cutting
computing
delay
overhead
