摘要
通过分析云系统中服务器的工作过程,提出将带有关停延迟机制的Geomξ/G/1排队模型应用到云计算关闭/休眠技术中的思想。针对云系统中任务到达的突发性,将嵌入马尔科夫链的方法应用到模型的理论分析中,导出云计算系统中平均等待任务数、能耗节省率、系统状态切换率和系统运行效率等系统性能指标的表达式。通过数值例子展示相关能耗性能指标与系统配置参数之间的依赖关系,分析任务到达突发性的大小对云系统性能指标的影响。研究成果为云计算中关闭/休眠技术参数配置提供了理论依据。
After analyzing the working process of the server in cloud system,an idea of applying Geomξ/G/1queuing model with close delay mechanism to off/sleep technology in cloud computing was proposed.Aiming at the burst arrival of the tasks in cloud system,using the embedded Markov chain method to analyze the queuing model,the mathematical expressions of system performance measures were derived,such as average number of waiting tasks,energy saving rate,switching rate of system state and system efficiency.Related numerical examples were intuitively given to show the dependency relationships between configuration parameters and system performance measures,the effects of different bursts on system performance measures were analyzed.The analysis results provide theoretical bases for the parameter configuration of off/sleep in cloud computing.
出处
《计算机工程与设计》
北大核心
2016年第2期507-511,518,共6页
Computer Engineering and Design
基金
国家自然科学基金项目(61472342)
关键词
云系统
突发性
随机任务
离散时间排队论
关闭/休眠技术
性能分析
cloud system
burst
stochastic tasks
discrete-time queuing theory
off/sleep technology
performance analysis
