Abstract: Concerning the problems of low energy efficiency and unreliable power failure in cloud, a PM integration mechanism and a scheduling algorithm are proposed, to improve energy efficiency while ensuring the reliability of cloud computing. Energy optimization mechanism can detect the optimization time, execute scheduling algorithms when the power failure. The algorithm adjusts the mapping of virtual machines to physical hosts, allocating the idle CPU capacity to the running virtual machines. The experimental results show that, compared with the traditional scheduling algorithms, the proposed technique improves energy efficiency of 15.8%, the energy consumption is reduced by 9.8%.

Key words: cloud computing, virtualization technology, energy efficiency, task deadline, reliability

摘要： 针对当前云计算能源效率低以及电源故障等不可靠问题，提出了一种物理主机整合机制以及调度算法，在保障云计算可靠性的同时提高能源效率。能量优化机制可以察觉优化时机，在电源等故障时执行调度算法。算法调节虚拟机到物理主机的映射，同时将相应物理主机中空闲的CPU容量，分配到正在运行的虚拟机中，从而提高能源效率。实验结果表明，与传统的调度算法相比，该算法在工作效率上提高了15.8%，在能量消耗上降低了9.8%。

关键词: 云计算, 虚拟化技术, 能源效率, 任务截止时间, 可靠性