A Clustered Virtual Machine Allocation Strategy Based on an N-Threshold Sleep-Mode in a Cloud Environment

In an effort to improve the energy efficiency of cloud data centers, in this paper, we propose a clustered Virtual Machine (VM) allocation strategy based on an N-threshold sleep-mode in which all the VMs in a cloud data center are clustered into two modules. The VMs in Module I are always awake, whereas the VMs in Module II will go to sleep under a light traffic load. When the number of waiting requests reaches or exceeds the threshold N, sleeping VMs will resume processing requests independently after their corresponding sleep timers expire. Accordingly, we establish an N-policy partially asynchronous multiple vacations queueing model, and derive the energy saving rate of the system. Numerical results are provided to show the efficiency of the proposed strategy in reducing energy consumption.