Abstract

The global energy efficiency of data centers across multiple geographically heterogeneous environments is studied in this paper. The resource provisioning of multiple data centers is formatted as a multi-objective optimization model. Aiming at this issue, four algorithms are proposed, CMM, MCMP based on green cloud priority and PMM, MPMC based on profit priority. The carbon emission, energy, profit and QoS are considered in algorithms synthetically. The goal is to reduce carbon emission and increase revenue with meeting QoS. For optimizing energy efficiency further, we prove that the energy consumption could reach a local munimum at the optimal CPU frequency. The experimental results show that the strategies not only reduce the energy costs, optimize the task scheduling and also balance the carbon footprint.

Paper Details