Reducing Resource Over-Provisioning Using Workload Shaping for Energy Efficient Cloud Computing

Abstract

Using workload shaping technology, we present an approach to remove hardware over-provisioning implementing task buffers and scheduler, in terms of energy consumption. Task buffers reorder tasks with various priorities and routes them to appropriate virtual machines. Scheduler monitors the task buffering and hardware load status, and decides the optimal number of active physical and virtual machines. In addition, we designed a mechanism wherein tasks with fast executing are routed in fast and high energy consumption machines and slow tasks to slow and low energy consumption machines. As a result, our approach efficiently can shape workloads and manage the optimal number of active virtual machines and physical machines, in terms of energy consumption. To evaluate our approach, we generated synthetic workload data and evaluated it both in simulating and actual cloud environment. Our experimental results demonstrate our approach outperforms in terms of energy consumption to when not using no workload shaping methodology.