Energy-Efficient Computation Offloading in Cloudlet-Based Mobile Cloud Using NSGA-II

摘要

Cloudlet is a novel computing paradigm, introduced to the mobile cloud service framework, aiming to alleviate the communication delay between the mobile devices and the cloud platform. Currently, the mobile applications, modeled by the workflows, tend to be complicated and computation-intensive. Such workflows are required to be offloaded to the cloudlet or the remote cloud platform for execution. However, it is still a key challenge to determine the offloading solutions for the deadline-constrained workflows in the cloudlet-based mobile cloud, since a cloudlet often has limited resources. In this paper, an Energy-efficient Computation Offloading method, named ECO, is proposed to address the above challenge. Technically, an energy consumption model for computing tasks is established in the cloudlet-based mobile computing. Then a corresponding computation offloading method, by leveraging NSGA-II (Non-dominated Sorting Genetic Algorithm II), is designed to achieve the goal of energy saving for each mobile device, while satisfying the deadline constraints. Finally, extensive experimental evaluations are conducted to demonstrate the efficiency and effectiveness of our proposed method.