面向绿色云计算数据中心的动态数据聚集算法

Dynamic data aggregation algorithm for data centers of green cloud computing

在分析目前云数据中心设备能耗和数据访问规律的基础上,创建了云计算数据模型,研究了云计算系统任务调度和数据部署层面的节能机制,提出一种面向绿色云计算数据中心的动态数据聚集算法。算法分为数据聚集与节点聚集两个层次,在兼顾系统服务质量的同时,按照节点和数据在不同时段的使用情况有效聚集数据,实现原本随机部署的数据与节点的有序化聚集和重新部署,从而使计算存储节点能够轮流运转,部署于云数据中心各区域的温控设备可以更加精确地实施定点环境温度控制。算法达到既充分利用资源,满足用户的服务需求,同时降低系统的整体能耗的目标。通过仿真实验进行了实验验证和性能分析,结果表明算法能够保障云数据中心的服务质量,提高设备稳定性,达到了"绿色"节能目标。

The current data center equipment energy consumption and data access laws are analyzed. Based on the research result, the cloud data model is created, and the energy-saving technologies are researched based on cloud task scheduling and data deployment, then a novel dynamic data aggregation algorithm is proposed for green cloud data centers. The data aggregation algorithm is divided into two levels： data aggregation and node aggregation. The main idea of this algorithm is that, with the consideration of quality of service, the data can be aggregated reasonably according to the data access laws in order to realize the orderly aggregation and re-deploy- ment of data and nodes deployed randomly before. The computing and storage nodes can take turns running, re- sulting in the accurate, highly-targeted temperature control of cooling equipment cooperating with servers. The algorithm achieves the goals of full use of resources, meeting the needs of users and reducing the overall system energy consumption. The results of the simulation experiments and the analysis of performance show that the proposed algorithm can maintain the quality of service for cloud data centers, improve the equipment reliability and achieve the ＂green＂ energy-saving goal.