An adaptive deadline constrained energy‐efficient scheduling heuristic for workflows in clouds
Wei Zheng, Shouhui Huang · Concurrency and Computation Practice and Experience · 2015
Summary There is an increasing interest for cloud services to be provided in a more energy‐efficient way. The growing deployment of large‐scale, complex workflow applications onto cloud computing hosts are facing with crucial challenges in reducing the energy consumption without violating certain quality of service. Dynamic voltage and frequency scaling (DVFS) is a power management technique commonly used to lower the processor frequency and decrease the energy consumption in modern computing systems. However, as lowering processor frequency may result in increased idle time on processors, which may in turn lead to increased overall energy consumption, scaling the processor frequency as low as possible may not always be energy‐efficient. In this paper, we consider cloud hosts with the DVFS technique and focus on the problem of scaling frequency to reduce overall energy consumption of a workflow given an allocation of tasks to hosts and a deadline to complete the execution. We propose a novel scheduling heuristic, which takes the system and application characteristics and the overall energy consumption into account when making frequency scaling decision. The proposed heuristic is evaluated using simulation with four different real‐world applications. The observed results indicate that our heuristic can achieve significant energy saving and outperform the existing approaches. Copyright © 2015 John Wiley & Sons, Ltd.