A Schedule Method for Parallel Applications on Heterogeneous Distributed Systems with Energy Consumption Constraint
HU Feng-song, Xiajie Quan, Can Lu · 2018
Energy consumption has become a key issue from small embedded devices to large-scale data centers. Recent studies are used to study the problem of minimizing the schedule length while satisfying the energy consumption constraint of parallel applications by transferring the energy constraint of the application to that of each task based on the dynamic voltage and frequency scaling (DVFS) technique. State-of-the-art algorithm has proposed an efficient scheduling algorithm using a relative average assignments for tasks. However, the method still does not reach the limit of the minimum scheduling length. In this study, we propose an efficient and provable scheduling algorithm using a relative weighed average assignments for tasks. A large number of experiments show that the proposed algorithm not only the energy consumption constraint pretty close but not over, but also the schedule length becomes shorter.