A Dynamic Consolidation of Virtual Machines Energy-Efficient Scheme based on User Task Characteristic

Idle for node cloud computing environment due to the randomness of the user task arrival caused a large number of idle energy consumption. To solve this problem, a dynamic consolidation of virtual machines energy-efficient scheme based on user task characteristic is proposed. First, the amount of tasks to achieve the statistical variation of task completion times user expectations, establish user tasks characteristic information table to predict the probability that the next time the user requests and expect to reach the finish time. Then, according to user expectations completion time, get psychological expectations QOS value of the user, and dynamically adjusts the threshold based on the integration of energy-saving value. Finally, dynamic integration and close idle node based on the user task arrival rate so as to achieve energy-saving purposes. Experimental results show that the method can accord user needs, a better balance of performance and energy saving.