云环境中面向随机任务的用户效用优化模型  

Random Task-Oriented User Utility Optimization Model in the Cloud Environment

作　　者：唐卓[1,2] 朱敏[1] 杨黎[3] 唐小勇[1] 李肯立[1] 

机构地区：[1]湖南大学信息科学与工程学院,长沙410082 [2]软件工程国家重点实验室(武汉大学),武汉430072 [3]长沙理工大学计算机与通信工程学院,长沙410114

出　　处：《计算机研究与发展》2014年第5期1120-1128,共9页Journal of Computer Research and Development

基　　金：国家自然科学基金重点项目(61133005);国家自然科学基金项目(61070057,61103047);武汉大学软件工程国家重点实验室开放基金项目(SKLSE2012-09-18)

摘　　要：资源分配方法和技术一直是云计算领域中的热点问题,现有的解决方案在资源分配与调度方面未能充分考虑用户的实际需要,首先通过引入用户效用的概念,建立了云环境中用户效用的描述模型,给出了用户对任务执行时间和费用满意程度的量化方法,并针对用户任务到达时间和任务类型的随机性,基于线性规划理论提出了云环境中面向用户效用的任务调度优化模型.该模型以任务完成的总效用值为目标,以用户任务的预期时间、费用和并行加速比为约束条件,能真实描述用户任务的随机性,面向时间和费用两个现实目标,求解出最合适的计算资源和排队秩序.最后通过实验表明,这种云环境中的任务调度方法能有效地满足用户对任务执行时间和费用的需求.Resource allocation methods and technology have always been a hot issue in the field of cloud computing. The existing solutions for resource allocation have not considered the actual requirement of the users so far. Through introducing the concept： utility, this paper proposes a description model for the user＇s utility in the cloud environment, which quantifies the user＇ satisfaction about the time and cost of the task in the cloud environment. Considering the randomness of the arrival time and the type of the tasks, this paper proposes an optimization model of task scheduling based on the theory of linear programming, using the basic concepts of user utility. This model takes the total utility value of the tasks completion as a goal, and takes the user tasks＇ expected time, cost and parallel speed-up ratio as the constraint condition. It can describe the randomness of the user＇s tasks, and choose the fittest resources which maximize the needs of every user while keeping the interests of other users. Finally, the simulation results verify the user utility optimization model of this paper.

关 键 词：云计算 随机任务 用户效用 线性规划 资源分配 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]