Towards energy-efficient scheduling for real-time tasks under uncertain cloud computing environment

Green cloud computing has become a major concern in both industry and academia, and efficient scheduling approaches show promising ways to reduce the energy consumption of cloud computing platforms while guaranteeing QoS requirements of tasks. Existing scheduling approaches are inadequate for realtime tasks running in uncertain cloud environments, because those approaches assume that cloud computing environments are deterministic and pre-computed schedule decisions will be statically followed during schedule execution. In this paper, we address this issue. We introduce an interval number theory to describe the uncertainty of the computing environment and a scheduling architecture to mitigate the impact of uncertainty on the task scheduling quality for a cloud data center. Based on this architecture, we present a novel scheduling algorithm (PRS) that dynamically exploits proactive and reactive scheduling methods, for scheduling real-time, aperiodic, independent tasks. To improve energy efficiency, we propose three strategies to scale up and down the system’s computing resources according to workload to improve resource utilization and to reduce energy consumption for the cloud data center. We conduct extensive experiments to compare PRS with four typical baseline scheduling algorithms. The experimental results show that PRS performs better than those algorithms, and can effectively improve the performance of a cloud data center.