摘要
云计算数据中心由通过高速网络连接的大量服务器构成,一种有效的节能措施是维持与系统负载成比例的活跃服务器数量同时切换剩余服务器到空闲模式,由此分别产生了操作能耗和切换能耗.研究在不同服务时隙内负载已知情况下,如何配置活跃服务器数量以最小化数据中心能耗的问题.首先,建立了问题的NP数学模型;然后分析了无切换能耗情况下最优解的特性;最终通过消除整数动态规划的递推过程,得到具有多项式复杂度的最优算法.数值结果表明,最优算法在不同负载变化趋势下保证能耗达到最小的同时保证计算过程平稳.
Cloud computing data centers generally consist of a large number of servers connected via high speed network. One promis- ing approach to saving energy is to maintain enough active severs in proportion to system load, while switch left servers to idle mode whenever possible. Then operating cost and switching cost is brought about respectively. The problem of fight-sizing active severs to minimize energy consumption in data centers is discussed assuming the average load of every time-slot to be given. Firstly,the NP- hard model is established, and the characteristics of the optimal solution when omitting the switching cost are analyzed. Then by revi- sing the solution procedure carefully, the recursive procedure is successfully eliminated. The optimal algorithm with polynomial com- plexity is achieved finally. Numerical results for variation tendency of different loads show that the proposed algorithm can guarantee minimum power consumption with a smooth computing process.
出处
《小型微型计算机系统》
CSCD
北大核心
2015年第12期2803-2807,共5页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61370088)资助
国家国际科技合作专项项目(2014DFB10060)资助
中央高校基本科研业务费专项资金项目(2011HGBZ1321
2012HGQC0012)资助
关键词
云计算数据中心
活跃服务器
动态规划
最优算法
clouding calculating data center
active servers
dynamic programming
optimal algorithm
