论文部分内容阅读
随着云计算的飞速发展,越来越多的人们选择在云数据中心完成他们的工作,云数据中心产生的巨大能源消耗成为不容忽视的问题。为了降低能源消耗实现绿色云计算,提出一种基于备用虚拟机同步休眠的云数据中心节能策略。系统中的虚拟机分为两大模块:主模块和备用模块。主模块一直处于活跃状态。根据云数据中心的工作负载轻重,备用模块处于休眠状态或者活跃状态。考虑为多任务用户请求提供服务的云数据中心,建立一个批量到达且部分服务台同步多重休假的排队模型。采用高斯赛德尔法,求解系统模型的稳态分布,给出系统节能率等性能指标表达式。进行数值实验和仿真实验,研究基于备用虚拟机同步休眠的云数据中心节能策略的系统性能,并验证所提策略的有效性。
With the rapid development of cloud computing, more and more people choose to complete their work in the cloud data center. The huge energy consumption in the cloud data center becomes a problem that can not be ignored. In order to reduce the energy consumption and realize the green cloud computing, a cloud data center energy-saving strategy based on standby virtual machine synchronization dormancy is proposed. The virtual machine in the system is divided into two major modules: the main module and the spare module. The main module is always active. Depending on the workload of the cloud data center, the standby module is in hibernation or active. Consider a cloud data center that serves multitasking users and build a queuing model that arrives in bulk and some help desk synchronizes multiple vacations. Using Gauss-Seidel method, the steady-state distribution of the system model is solved, and the expression of performance index such as the energy-saving rate of the system is given. Numerical experiments and simulation experiments are conducted to study the system performance of cloud data center energy-saving strategy based on standby virtual machine synchronization dormancy and to verify the effectiveness of the proposed strategy.