系统工程与电子技术 ›› 2020, Vol. 42 ›› Issue (6): 1386-1394.doi: 10.3969/j.issn.1001-506X.2020.06.24

• 通信与网络 • 上一篇    下一篇

基于MEC的任务卸载和资源分配联合优化方案

黄晓舸(), 崔艺凡(), 张东宇(), 陈前斌()   

  1. 重庆邮电大学通信与信息工程学院, 重庆 400065
  • 收稿日期:2019-09-11 出版日期:2020-06-01 发布日期:2020-06-01
  • 作者简介:黄晓舸(1982-),女,副教授,博士,主要研究方向为移动通信技术、认知无线电动态频谱分配。E-mail:huangxg@cqupt.edu.cn|崔艺凡(1996-),女,硕士研究生,主要研究方向为移动通信技术、小蜂窝网络。E-mail:cuiyifan1118@foxmail.com|张东宇(1993-),男,硕士,主要研究方向为认知无线电网络、无线通信和小蜂窝网络。E-mail:zhangdongyu@outlook.com|陈前斌(1967-),男,教授,博士研究生导师,博士,研究方向为新一代移动通信系统、未来网络和LTE-Advanced异构小蜂窝网络。E-mail:chenqb@cqupt.edu.cn
  • 基金资助:
    国家自然科学基金重点项目(61831002);重庆市科委重庆市基础研究与前沿探索项目(cstc2018jcyjAx0383)

Joint optimization scheme of task offloading and resource allocation based on MEC

Xiaoge HUANG(), Yifan CUI(), Dongyu ZHANG(), Qianbin CHEN()   

  1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2019-09-11 Online:2020-06-01 Published:2020-06-01
  • Supported by:
    国家自然科学基金重点项目(61831002);重庆市科委重庆市基础研究与前沿探索项目(cstc2018jcyjAx0383)

摘要:

面对时延敏感度不同的多种用户,如何有效利用频谱资源和计算资源受限的边缘节点来保障其时延能耗需求成为关键问题。为此,提出了基于移动边缘计算(mobile edge computing, MEC)的任务卸载和资源分配联合优化方案。首先,为最小化卸载任务在MEC的总计算时间,给每个用户分配最优的MEC计算资源。其次,基于时延敏感度、用户满意度和资源块(resource block, RB)质量,引入RB分配算法,以分布式执行。最后,用户通过比较本地计算开销和卸载计算开销做出卸载决策。仿真结果表明,所提算法在满足高时延敏感用户的需求前提下,通过有效地分配传输资源和计算资源,实现了最小的系统开销。

关键词: 资源分配, 移动边缘计算, 时延敏感度, 卸载决策

Abstract:

Faced with multiple users with different delay sensitivities, how to effectively use transmission resources and computing resources in limited edge nodes to ensure the delay and energy requirements of users becomes a key issue. To this end, a joint optimization scheme based on mobile edge computing (MEC) for task offloading and resource allocation is proposed. Firstly, to minimize the total computation time of the offloading tasks at MEC, each user is assigned with the optimal MEC computing resource. Secondly, a resource block (RB) distribution algorithm based on the delay-sensitive, satisfaction degree and quality of RBs is introduced in a distributed manner. Finally, each user makes the offloading decision by comparing the local computational overhead with the offloading computational overhead. The simulation results show that the proposed algorithm achieves the minimum system overhead by effectively allocating transmission resources and computing resources under the premise of meeting the requirements of high-latency sensitive users.

Key words: resource allocation, mobile edge computing (MEC), delay-sensitive, offloading decision

中图分类号: