A Task Scheduling Method for Energy-Performance Trade-Off in Clouds
Jun Qiang Yang, Xiaolong Xu, Wenda Tang, Chunhua Hu, Wanchun Dou, Jinjun Chen · 2016
Energy consumption is an increasingly important issue for profit-driven cloud. Meanwhile, meeting users' expected response time is crucial for the real-time tasks. However, minimizing energy consumption may delay response time during task scheduling. Unfortunately, existing scheduling algorithms remain limit in balancing energy-saving and performance in elastic cloud environment. In view of this challenge, a task scheduling method for trade-off between energy and performance is proposed in this paper. Firstly, the energy-aware task scheduling problem in clouds is modeled by incorporating the virtualization technology. Then, an energy-aware resource provisioning algorithm is developed for generating available allocation plans for real time task by exploiting the elasticity of virtual resources. Finally, an energy-performance trade-off scheduling algorithm is designed for selecting final solution based on multi-objective optimization. The experimental evaluations are presented for validating our method.