ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (3): 537-550.doi: 10.7544/issn1000-1239.2018.20170714

所属专题: 2018边缘计算专题

• 网络技术 • 上一篇    下一篇



  1. 1(南开大学计算机与控制工程学院 天津 300071); 2(广东省大数据分析与处理重点实验室(中山大学) 广州 510006) (
  • 出版日期: 2018-03-01
  • 基金资助: 

Joint Task Offloading and Base Station Association in Mobile Edge Computing

Yu Bowen1, Pu Lingjun1,2, Xie Yuting1, Xu Jingdong1, Zhang Jianzhong1   

  1. 1(College of Computer and Control Engineering, Nankai University, Tianjin 300071); 2(Guangdong Key Laboratory of Big Data Analysis and Processing (Sun Yat-Sen University), Guangzhou 510006)
  • Online: 2018-03-01

摘要: 为了缩小IoT应用的服务质量要求与IoT设备有限的计算资源之间的差距,提高设备与基站能源利用率,设计了基于超密集网络的移动边缘计算框架COMED,提出了一个结合任务卸载、设备-基站关联以及基站睡眠调度的在线优化问题,旨在最小化设备和基站的整体能量消耗,同时满足IoT应用的服务质量要求.针对这一在线优化问题,提出了一个基于李雅普诺夫优化理论的任务调度算法JOSA,该算法只使用当前时间片的系统信息进行调度.仿真实验证明了COMED框架具有良好的性能:1)与设备本地处理相比,系统整体节能30%以上,与DualControl算法相比平均节能10%~50%;2)算法的执行时间与IoT设备数量呈近似线性的关系.

关键词: 移动边缘计算, 任务卸载, 基站睡眠, 设备-基站关联, NP难问题

Abstract: In order to narrow the gap between the requirements of IoT applications and the restricted resources of IoT devices and achieve devices energy efficiency, in this paper we design COMED, a novel mobile edge computing framework in ultra-dense mobile network. In this context, we propose an online optimization problem by jointly taking task offloading, base station (BS) sleeping and device-BS association into account, which aims to minimize the total energy consumption of both devicesand BSs, and meanwhile satisfies applications’ QoS. To tackle this problem, we devise an online Lyapunov-based algorithm JOSA by exploiting the system information in the current time slot only. As the core component of this algorithm, we resort to the loose-duality framework and propose an optimal joint task offloading, BS sleeping and device-BS association policy for each time slot. Extensive simulation results corroborate that the COMED framework is of great performance: 1) more than 30% energy saving compared with local computing, and on average 10%-50% energy saving compared with the state-of-the-art algorithm DualControl (i.e., energy-efficiency); 2) the algorithm running time is approximately linear proportion to the number of devices (i.e., scalability).

Key words: mobile edge computing, task offloading, base station (BS) sleeping, device-BS association, NP-hard problem