Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (2): 36-43.DOI: 10.3778/j.issn.1002-8331.1806-0139

Previous Articles     Next Articles

Computation Offloading for Service Workflow in Mobile Edge Computing

DONG Hao1, ZHANG Haiping2, LI Zhongjin1, LIU Hui1   

  1. 1.School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China
    2.College of Information Engineering, Hangzhou Dianzi University, Hangzhou 310018, China
  • Online:2019-01-15 Published:2019-01-15


董  浩1,张海平2,李忠金1,刘  辉1   

  1. 1.杭州电子科技大学 计算机科学与技术学院,杭州 310018
    2.杭州电子科技大学 信息工程学院,杭州 310018

Abstract: Mobile Edge Computing(MEC) moves computation and storage resources to the edge of the mobile network, enabling it to run applications that require high processing at the mobile device while meeting stringent delay requirements. This paper considers the issue of mobile computing offloading, in which multiple mobile services in a workflow can be invoked to meet their complex needs and decide whether to uninstall workflow services, taking into account the dependencies between the component services, and aims to optimize the execution time and energy consumption of executing mobile services. A GA-based algorithm is applied to the above problems. After design and implementation, it partially modifies the traditional genetic algorithm to meet special requirements for the problem. Simulation experiments show that the experimental results of GA algorithm are better than Local Execution algorithm and RANDOM algorithm.

Key words: mobile edge computing, computation offloading, Genetic Algorithm(GA), service workflow

摘要: 移动边缘计算(MEC)将计算和存储资源移动到移动网络的边缘,使其能够在满足严格的延迟要求的同时在移动设备处运行要求高处理的应用。它考虑了移动计算卸载问题,其中可以调用工作流中的多个移动服务来满足其复杂需求,并决定是否卸载工作流的服务,同时考虑了组件服务之间的依赖关系,并旨在优化执行移动服务的执行时间和能耗。针对上述问题运用了基于遗传算法(GA)的卸载方法,经过设计和实施后,部分修改传统遗传算法,以满足对所述问题的特殊需求。仿真实验表明,GA算法的实验效果都优于算法Local Execution和RANDOM得到的实验结果。

关键词: 移动边缘计算, 计算卸载, 遗传算法, 服务工作流