MEC计算卸载与资源分配联合智能优化方案

doi:10.13190/j.jbupt.2021-145

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (2): 65-71.doi: 10.13190/j.jbupt.2021-145

MEC计算卸载与资源分配联合智能优化方案

杜梅¹, 周军华², 李敦桥³, 陈士钊⁴, 魏翼飞¹

1. 北京邮电大学电子工程学院, 北京 100876;
2. 北京市复杂产品先进制造工程研究中心北京市仿真中心, 北京 100854;
3. 贵州航天控制技术有限公司, 贵阳 550009;
4. 宁波中湾科技有限公司, 宁波 315400

收稿日期:2021-07-21 发布日期:2021-12-16
作者简介:杜梅(1996—),女,硕士生,邮箱:dmxy54210383@163.com;魏翼飞(1983—),男,教授。
基金资助:
国家自然科学基金项目(61871058)

A Joint Intelligent Optimization Scheme of Computation Offloading and Resource Allocation for MEC

DU Mei¹, ZHOU Junhua², LI Dunqiao³, CHEN Shizhao⁴, WEI Yifei¹

1. School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Beijing Simulation Center, Beijing Advanced Manufacturing Engineering Research Center for Complex Products, Beijing 100854, China;
3. Guizhou Aerospace Control Technology Limited Company, Guiyang 550009, China;
4. Ningbo Zhongwan Technology Limited Company, Ningbo 315400, China

Received:2021-07-21 Published:2021-12-16

摘要/Abstract

摘要： 移动边缘计算(MEC)中的分布式基站部署、有限的服务器资源和动态变化的终端用户使得计算卸载方案的设计极具挑战。鉴于深度强化学习在处理动态复杂问题方面的优势,设计了最优的计算卸载和资源分配策略,目的是最小化系统能耗。首先考虑了云边端协同的网络框架;然后将联合计算卸载和资源分配问题定义为一个马尔可夫决策过程,提出一种基于多智能体深度确定性策略梯度的学习算法,以最小化系统能耗。仿真结果表明,该算法在降低系统能耗方面的表现明显优于深度确定性策略梯度算法和全部卸载策略。

关键词: 移动边缘计算, 计算卸载, 资源分配, 多智能体强化学习

Abstract: Due to the distributed base station deployment, limited server resources and dynamic end-users in mobile edge computing (MEC), the design of computation offloading scheme is extremely challenging. Since the deep reinforcement learning has advantages in terms of dealing with dynamic complex problems, we design the optimal computation offloading and resource allocation strategies based on deep reinforcement learning to minimize the system energy consumption. First, the network framework of cloud edge-end collaboration is considered. Then, the joint computation offloading and resource allocation problem is defined as a Markov decision process.Next, a multi-agent deep deterministic policy gradient-based learning algorithm is proposed to minimize the system energy consumption. The experimental results show that our proposed scheme significantly reduces the energy consumption compared to the deep deterministic policy gradient-based algorithm and the full offloading policy.

Key words: mobile edge computing, computation offloading, resource allocation, multi-agent reinforcement learning

中图分类号:

TP391.4

杜梅, 周军华, 李敦桥, 陈士钊, 魏翼飞. MEC计算卸载与资源分配联合智能优化方案[J]. 北京邮电大学学报, 2022, 45(2): 65-71.

DU Mei, ZHOU Junhua, LI Dunqiao, CHEN Shizhao, WEI Yifei. A Joint Intelligent Optimization Scheme of Computation Offloading and Resource Allocation for MEC[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(2): 65-71.

参考文献

[1] ABBAS N, ZHANG Y, TAHERKORDI A, et al. Mobile edge computing:a survey[J]. IEEE Internet of Things Journal, 2018, 5(1):450-465.
[2] MACH P, BECVAR Z. Mobile edge computing:a survey on architecture and computation offloading[J]. IEEE Communications Surveys and Tutorials, 2017, 19(3):1628-1656.
[3] WANG Y, GE H, FENG A, et al. Computation offloading strategy based on deep reinforcement learning in cloud-assisted mobile edge computing[C]//2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA). Piscataway, NJ:IEEE Press, 2020:108-113.
[4] DAI Y, ZHANG K, MAHARJAN S, et al. Edge intelligence for energy-efficient computation offloading and resource allocation in 5G Beyond[J]. IEEE Transactions on Vehicular Technology, 2020, 69(10):12175-12186.
[5] LIANG H, XU F, CHENG Z, et al. Deep reinforcement learning-based joint task offloading and bandwidth allocation for multi-user mobile edge computing[J]. Digital Communications and Networks, 2019, 5(1):10-17.
[6] LV J F, XIONG J Y, GUO H Z, et al. Joint computation offloading and resource configuration in ultra-dense edge computing networks:a deep reinforcement learning solution[C]//VTC2019-Fall. Piscataway, NJ:IEEE Press, 2019:1-5.
[7] LOWER R, WU Y, TAMAR A, et al. Multiagent actor-critic for mixed cooperative-competitive environments[C]//International Conference on Neural Information Processing Systems.Piscataway, NJ:IEEE Press, 2017:6382-6393.
[8] ZHAO J H, LI Q P, GONG Y, et al. Computation offloading and resource allocation for cloud assisted mobile edge computing in vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2019, 68(8):7944-7956.
[9] NGUYEN T T, LE L B. Computation offloading in MIMO based mobile edge computing systems under perfect and imperfect CSI estimation[C]//2018 IEEE International Conference on Communications (ICC).Piscataway, NJ:IEEE Press, 2018:1-6.
[10] DAI Y Y, XU D, MAHARJAN S, et al. Joint computation offloading and user association in multi-task mobile edge computing[J]. IEEE Transactions on Vehicular Technology, 2018, 67(12):12313-12325.
[11] XIAO J, YANG C G, ANPALAGAN A, et al. Joint interference management in ultra-dense small-cell networks:a multi-domain coordination perspective[J]. IEEE Transactions on Communications, 2018, 66(11):5470-5481.
[12] YU Y H, ZHANG J, LETAIEF K B. Joint subcarrier and CPU time allocation for mobile edge computing[C]//2016 IEEE Global Communications Conference. Piscataway, NJ:IEEE Press, 2016:1-6.
[13] BLUM L, SHUB M, SMALE S. On a theory of computation over the real numbers; NP completeness, recursive functions and universal machines[C]//29th Annual Symposium on Foundations of Computer Science. Piscataway, NJ:IEEE Press, 1988:387-397.

[1]	黄龙杨张楠刘笑笑申滨. 异构蜂窝网络中基于雾节点协作贡献度的计算卸载算法[J]. 北京邮电大学学报, 2023, 46(2): 37-42.
[2]	彭维平王戈宋成阎俊豪. 面向高移动性车联网场景的预测卸载决策算法[J]. 北京邮电大学学报, 2023, 46(2): 43-49.
[3]	魏明亮耿绥燕赵雄文胡玮范静怡. 超密集网络中移动边缘计算的资源分配和任务卸载联合优化研究[J]. 北京邮电大学学报, 2023, 46(2): 50-56.
[4]	公雨魏翼飞. 一种集成学习辅助DDPG的资源优化算法[J]. 北京邮电大学学报, 2023, 46(2): 29-36.
[5]	付志远施丽琴叶迎晖卢光跃. 反向散射辅助的无线供能NOMA-MEC网络中公平性优化研究[J]. 北京邮电大学学报, 2023, 46(2): 71-77.
[6]	彭维平杨玉莹宋成阎俊豪. VEC中多边缘节点协作卸载与资源分配算法[J]. 北京邮电大学学报, 2023, 46(2): 78-83.
[7]	郭兴康孙君. 基于交替方向乘子法与深度强化学习算法的资源分配[J]. 北京邮电大学学报, 2022, 45(6): 126-130.
[8]	李松王新荣王博文孙彦景陈瑞瑞. 基于随机网络演算的车联网边缘计算性能分析[J]. 北京邮电大学学报, 2022, 45(5): 16-22.
[9]	郁小松, 朱青橙, 顾佳明, 赵永利, 张杰. 云边协同光量子物联网架构及资源分配[J]. 北京邮电大学学报, 2022, 45(3): 50-56.
[10]	郅佳琳, 王楠, 满毅, 滕颖蕾. 面向硬件感知的边缘计算卸载和资源分配[J]. 北京邮电大学学报, 2022, 45(2): 22-28.
[11]	张雨晴, 李云, 黄鸿锐, 庄宏成. 异构网络中任务卸载与资源分配联合优化算法[J]. 北京邮电大学学报, 2022, 45(2): 91-97.
[12]	贾雨宁, 魏翼飞, 周军华. 基于SDN与NFV的服务功能链编排算法[J]. 北京邮电大学学报, 2022, 45(2): 85-90.
[13]	高晓娜, 卢光跃, 叶迎晖, 昝金枚. 认知反向散射网络通信容量公平的资源优化[J]. 北京邮电大学学报, 2021, 44(6): 26-32.
[14]	郑远鹏, 张天魁, 朱光宇, 沈鸿. MEC系统中面向网络切片的3C联合资源分配算法[J]. 北京邮电大学学报, 2021, 44(5): 41-47.
[15]	陈伟, 霍如, 汪硕, 黄韬, 刘韵洁. 基于区块链的D2D辅助的MEC资源共享架构[J]. 北京邮电大学学报, 2021, 44(5): 1-9.

MEC计算卸载与资源分配联合智能优化方案

A Joint Intelligent Optimization Scheme of Computation Offloading and Resource Allocation for MEC

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价