面向移动边缘计算的联合计算卸载和资源分配策略研究

doi:10.3969/j.issn.1000-5641.2021.06.010

华东师范大学学报（自然科学版） ›› 2021, Vol. 2021 ›› Issue (6): 88-99.doi: 10.3969/j.issn.1000-5641.2021.06.010

面向移动边缘计算的联合计算卸载和资源分配策略研究

黄冬晴¹, 俞黎阳^1,*(), 陈珏², 魏同权¹

1. 华东师范大学计算机科学与技术学院, 上海　200062
2. 上海工程技术大学电子电气工程学院, 上海　201620

收稿日期:2020-06-22 出版日期:2021-11-25 发布日期:2021-11-26
通讯作者: 俞黎阳 E-mail:lyyu@cs.ecnu.edu.cn
基金资助:
上海市科学技术委员会项目(19YF1418300)

Research on joint computation offloading and resource allocation strategy for mobile edge computing

Dongqing HUANG¹, Liyang YU^1,*(), Jue CHEN², Tongquan WEI¹

1. School of Computer Science and Technology, East China Normal University, Shanghai　200062, China
2. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai　201620, China

Received:2020-06-22 Online:2021-11-25 Published:2021-11-26
Contact: Liyang YU E-mail:lyyu@cs.ecnu.edu.cn

摘要/Abstract

摘要：

随着无人驾驶、在线游戏、虚拟现实等低延迟应用的大量涌现, 传统集中式的移动云计算范式越来越难以满足此类用户服务质量的需求. 为弥补云计算的不足, 移动边缘计算应运而生. 移动边缘计算通过计算卸载, 将计算任务迁移到网络边缘服务器来为用户提供计算和存储资源. 然而, 现有大部分工作仅考虑了延迟或能耗的单目标性能优化, 未考虑延迟和能耗的均衡优化. 为减少任务延迟和设备能耗, 提出了一种面向多用户的联合计算卸载和资源分配策略. 该策略首先利用拉格朗日乘子法获得给定卸载决策的最佳计算资源分配; 然后, 提出一个基于贪心算法的计算卸载算法获得最佳卸载决策; 最后, 通过不断迭代得到最终解. 实验结果表明, 与基准算法相比, 所提算法最高可以降低40%的系统成本.

关键词: 移动边缘计算, 计算卸载, 资源分配, 拉格朗日乘子法, 贪心算法

Abstract:

With the emergence of low-latency applications such as driverless cars, online gaming, and virtual reality, it is becoming increasingly difficult to meet users’ demands for service quality using the traditional centralized mobile cloud computing model. In order to make up for the shortages of cloud computing, mobile edge computing came into being, which provides users with computing and storage resources by migrating computing tasks to network edge servers through computation offloading. However, most of the existing work processes only consider single-objective performance optimization of delay or energy consumption, and do not consider the balanced optimization of delay and energy consumption. Therefore, in order to reduce task delay and equipment energy consumption, a multi-user joint computation offloading and resource allocation strategy is proposed. In this strategy, the Lagrange multiplier method is used to obtain the optimal allocation of computing resources for a given offloading decision. Then, a computation offloading algorithm based on a greedy algorithm is proposed to obtain the optimal offloading decision; the final solution is obtained through continuous iteration. Experimental results show that, compared with the benchmark algorithm, the proposed algorithm can reduce system costs by up to 40%.

Key words: mobile edge computing, computation offloading, resource allocation, Lagrange multiplier method, greedy algorithm

中图分类号:

TP391

黄冬晴, 俞黎阳, 陈珏, 魏同权. 面向移动边缘计算的联合计算卸载和资源分配策略研究[J]. 华东师范大学学报（自然科学版）, 2021, 2021(6): 88-99.

Dongqing HUANG, Liyang YU, Jue CHEN, Tongquan WEI. Research on joint computation offloading and resource allocation strategy for mobile edge computing[J]. Journal of East China Normal University(Natural Science), 2021, 2021(6): 88-99.

图/表 6

图1

表1

图2

图3

图4

图5

参考文献 17

1	GOHIL A, MODI H, PATEL S K. 5G technology of mobile communication: A survey [C]// 2013 International Conference on Intelligent Systems and Signal Processing (ISSP). IEEE, 2013: 288-292.
2	MACH P, BECVAR Z. Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys and Tutorials, 2017, 19 (3): 1628- 1656. doi: 10.1109/COMST.2017.2682318
3	HU Y C, PATEL M, SABELLA D, et al. Mobile Edge Computing: A Key Technology Towards 5G [M]. [S.l.]: ETSI (European Telecommunications Standards Institute) , 2015.
4	ZHANG D Y, TANG J Z, DU W T, et al. Joint optimization of computation offloading and UL/DL resource allocation in MEC systems [C]// 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). IEEE, 2018: 6 pages. DOI: 10.1109/PIMRC.2018.8580841.
5	ALAM M G R, HASSAN M M, UDDIN M Z, et al. Autonomic computation offloading in mobile edge for IoT applications. Future Generation Computer Systems, 2019, 90, 149- 157. doi: 10.1016/j.future.2018.07.050
6	PAYMARD P, REZVANI S, MOKARI N. Joint task scheduling and uplink/downlink radio resource allocation in PD-NOMA based mobile edge computing networks. Physical Communication, 2019, 32, 160- 171. doi: 10.1016/j.phycom.2018.11.007
7	LIU J H, ZHANG Q. Computation resource allocation for heterogeneous time-critical IoT services in MEC [EB/OL]. (2020-02-12)[2020-05-30]. https://arxiv.org/abs/2002.04851.
8	GUO F X, ZHANG H L, JI H, et al. Energy efficient computation offloading for multi-access MEC enabled small cell networks [C]// 2018 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2018: 6 pages. DOI: 10.1109/ICCW.2018.8403701.
9	LI C L, TANG J H, ZHANG Y, et al. Energy efficient computation offloading for nonorthogonal multiple access assisted mobile edge computing with energy harvesting devices. Computer Networks, 2019, 164, 106890. doi: 10.1016/j.comnet.2019.106890
10	QIAN L P, ZHU Z Y, YU N N, et al. Joint minimization of transmission energy and computation energy for MEC-aware NOMA NB-IoT networks [C]// 2019 IEEE Global Communications Conference (GLOBECOM). IEEE, 2019: 7 pages. DOI: 10.1109/GLOBECOM38437.2019.9013350.
11	ZENG M, FODOR V. Energy minimization for delay constrained mobile edge computing with orthogonal and non-orthogonal multiple access. Ad Hoc Networks, 2020, 98, 102060. doi: 10.1016/j.adhoc.2019.102060
12	LI J, GAO H, LYU T J, et al. Deep reinforcement learning based computation offloading and resource allocation for MEC [C]// 2018 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2018: 6 pages. DOI: 10.1109/WCNC.2018.8377343.
13	HUANG C M, CHIANG M S, DAO D T, et al. V2V data offloading for cellular network based on the software defined network (SDN) inside mobile edge computing (MEC) architecture. IEEE Access, 2018, (6): 17741- 17755.
14	隋允康, 贾志超. 0-1线性规划的连续化及其遗传算法解法. 数学的实践与认识, 2010, 40 (6): 119- 127.
15	3GPP Technical Specification Group Radio Access Network. Further advancements for E-UTRA physical layer aspects(Release 9) [R]. 3GPP TS 36.814 V9.0.0, 2010.
16	CHEN M, HAO Y X. Task offloading for mobile edge computing in software defined ultra-dense network. IEEE Journal on Selected Areas in Communications, 2018, 36 (3): 587- 597. doi: 10.1109/JSAC.2018.2815360
17	SHAHZAD H, SZYMANSKI T H. A dynamic programming offloading algorithm for mobile cloud computing [C]// 2016 IEEE 9th International Conference on Cloud Computing (CLOUD). IEEE, 2016: 960-965.

符号	含义
$ N $	小区内移动设备/用户的总数
$ {B}_{i} $	用户 $ i $ 的计算任务数据大小
$ {C}_{i} $	用户 $ i $ 的计算任务完成所需的计算资源量
$ {a}_{\rm{i}} $	二进制卸载决策变量
$ {s}_{i} $	任务的计算资源分配变量
$ A $	所有任务卸载决策集合
${{S} }$	计算资源分配集合
$ K $	基站最多可以服务的用户数
$ B $	系统带宽
$ W $	用户带宽
$ {S}_{\rm{max}} $	MEC服务器上可用的最大计算资源量
$ {r}_{i} $	用户 $ i $ 的上行链路传输速率
$ {g}_{i} $	用户 $ i $ 与BS之间的信道增益
$ {\sigma }^{2} $	高斯信道噪声的方差
${f}_{{\rm{l}},{i}}$	本地设备CPU计算能力
$ {\varepsilon }_{i} $	用户设备能耗系数
${T}_{{\rm{l}},{i}}$	用户 $ i $ 的本地计算时延
${E}_{{\rm{l}},{i}}$	用户 $ i $ 的本地计算能耗
$ {p}_{i} $	用户设备传输功率
${p}_{{\rm{o}},{i}}$	用户设备空闲状态下电路功率
${T}_{ {\rm{e} },{i} }$	任务卸载到MEC服务器的时延
${E}_{{\rm{e}},{i}}$	任务卸载到MEC服务器的能耗
${\beta }_{{\rm{t}},{i}}$	用户 $ i $ 的任务时延偏好参数
${\beta }_{{\rm{e}},{i}}$	用户 $ i $ 的任务能耗偏好参数

[1]	唐海波, 林煜明, 李优. 一种基于K-Means的平衡约束聚类算法[J]. 华东师范大学学报(自然科学版), 2018, 2018(5): 164-171.
[2]	华夏渝;郑骏;胡文心. 基于云计算环境的蚁群优化计算资源分配算法[J]. 华东师范大学学报(自然科学版), 2010, 2010(1): 127-134.

面向移动边缘计算的联合计算卸载和资源分配策略研究

Research on joint computation offloading and resource allocation strategy for mobile edge computing

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 17

相关文章 2

编辑推荐

Metrics

本文评价