Energy-Aware Rolling-Horizon Scheduling for Real-Time Tasks in Virtualized Cloud Data Centers

Abstract

Developing energy-aware Cloud data centers not only can reduce power electricity cost but also can improve system reliability. Existing scheduling algorithms developed for energy-aware Cloud data centers commonly lack the consideration of task level scheduling. To address this issue, we propose a novel rolling-horizon scheduling architecture for real-time task scheduling. Besides, a task energy consumption model is given in detail. Based on the novel scheduling architecture, we develop a novel energy-aware scheduling algorithm EARH for real-time, aperiodic tasks. The EARH employs a rolling horizon optimization policy and can be extended to integrate other scheduling algorithms. Again, we propose the resource scaling up and scaling down strategies to make a good tradeoff between task's schedulability and energy saving. Extensive experiments are conducted to validate the superiority of our EARH by comparing it with three baselines. Experimental results show that EARH significantly improves the scheduling quality of others and it is suitable for real-time task scheduling in virtualized Cloud data centers.