Cloud data centers energy-saving scheduling algorithm based on CPU frequency scaling

Abstract

The high energy consumption in cloud data centers has become an urgent problem. The scale and architecture of cloud data centers are growing increasingly immense and complex in recent years, which bring more severe challenges on the energy consumption management. This paper proposes new approaches for virtual machines (VMs) placement based on CPU frequency scaling. In the stage of initial VM placement, we propose a multi-objective optimization approach based on a heuristic ant colony algorithm, which can satisfy energy saving as well as servicelevel agreement (SLA). In the stage of dynamic management, by using autoregressive prediction and CPU frequency scaling, the proposed approach can adjust the CPU utilization while reducing the VM migration times and the migration cost. The experiments results show that the energy saving algorithms based on CPU frequency scaling are much better than the traditional best fit descending and first fit descending methods in saving energy and satisfying SLA.