数字孪生云边网络下服务缓存与计算卸载优化

doi:10.16182/j.issn1004731x.joss.24-0574

系统仿真学报 ›› 2025, Vol. 37 ›› Issue (11): 2741-2753.doi: 10.16182/j.issn1004731x.joss.24-0574

• 论文 • 上一篇

数字孪生云边网络下服务缓存与计算卸载优化

郑家瑜¹^,²^,³, 麦著学¹^,²^,³, 陈哲毅¹^,²^,³

^1.福州大学计算机与大数据学院，福建福州 350116
^2.大数据智能教育部工程研究中心，福建福州 350002
^3.福建省网络计算与智能信息处理重点实验室(福州大学)，福建福州 350116

收稿日期:2024-05-27 修回日期:2024-07-30 出版日期:2025-11-18 发布日期:2025-11-27
通讯作者: 陈哲毅
第一作者简介:郑家瑜(2000-)，男，硕士生，研究方向为边缘计算、服务缓存、计算卸载。
基金资助:
国家自然科学基金(62202103);中央引导地方科技发展资金(2022L3004);福建省科技经济融合服务平台(2023XRH001);福厦泉国家自主创新示范区协同创新平台项目(2022FX5)

Optimization of Service Caching and Computation Offloading in Digital Twin Cloud-edge Networks

Zheng Jiayu¹^,²^,³, Mai Zhuxue¹^,²^,³, Chen Zheyi¹^,²^,³

^1.College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China
^2.Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China
^3.Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China

Received:2024-05-27 Revised:2024-07-30 Online:2025-11-18 Published:2025-11-27
Contact: Chen Zheyi

摘要/Abstract

摘要：

在移动边缘计算(mobile edge computing，MEC)中，针对如何联合优化服务缓存与计算卸载以满足用户多样化需求，以及不合理的资源分配导致了低效的资源利用等问题，提出了一种新颖的基于凸优化使能深度强化学习的服务缓存与计算卸载联合优化（joint optimization of service caching and computation offloading with convex-optimization-enabled deep reinforcement learning，JCO-CR)方法。构建了一种新型的数字孪生云边网络（digital twin cloud-edge networks，DTCEN)模型。将服务缓存与计算卸载联合优化问题解耦为两个子问题并采用改进的深度强化学习方法和凸优化理论分别求解。仿真实验结果表明：JCO-CR方法能够有效降低长期服务延迟，并在不同场景下均展现出更加优越的性能。

关键词: 移动边缘计算, 数字孪生, 服务缓存, 计算卸载, 深度强化学习, 凸优化

Abstract:

In mobile edge computing (MEC), to satisfy diverse user demands by jointly optimizing service caching and computation offloading and address low-efficiency resource utilization caused by irrational resource allocation, this paper proposed a novel joint optimization of service caching and computation offloading with a convex-optimization-enabled deep reinforcement learning (JCO-CR) method. Additionally, a new model for digital twin cloud-edge networks (DTCEN) was constructed. The joint optimization of service caching and computation offloading was decoupled into two sub-problems, which were solved by an improved deep reinforcement learning method and convex optimization theory, respectively. Simulation experiments demonstrate that the proposed JCO-CR method can reduce long-term service latency and achieve better performance under different scenarios.

Key words: mobile edge computing, digital twin(DT), service caching, computation offloading, deep reinforcement learning, convex optimization

中图分类号:

TP393

郑家瑜,麦著学,陈哲毅 . 数字孪生云边网络下服务缓存与计算卸载优化[J]. 系统仿真学报, 2025, 37(11): 2741-2753.

Zheng Jiayu,Mai Zhuxue,Chen Zheyi . Optimization of Service Caching and Computation Offloading in Digital Twin Cloud-edge Networks[J]. Journal of System Simulation, 2025, 37(11): 2741-2753.

图/表 7

图1

图2

表1

仿真参数设置

参数	值
BS数量I	3^[23]
BS的计算能力F/GHz	{12,18,24}
BS的存储容量C/GB	{10,15,20}
BS单时隙收到请求数N	[2,10]
训练回合E	5 000
时隙数T	144^[24]
任务大小d/kb	[200,400]
高斯噪声功率 $σ 2$ /dBm	-50^[18]
通信干扰功率 $I j', i$ /dBm	-60

表1

图3

图4

图5

图6

参考文献 26

[1]	Mario Sanz Rodrigo, Rivera Diego, José Ignacio Moreno, et al. Digital Twins for 5G Networks: A Modeling and Deployment Methodology[J]. IEEE Access, 2023, 11: 38112-38126.
[2]	李超, 李贾宝, 丁才昌, 等. 基于DRL的边缘监控任务卸载与资源分配算法[J]. 系统仿真学报, 2024, 36(9): 2113-2126.
	Li Chao, Li Jiabao, Ding Caichang, et al. Edge Surveillance Task Offloading and Resource Allocation Algorithm Based on DRL[J]. Journal of System Simulation, 2024, 36(9): 2113-2126.
[3]	Mach Pavel, Becvar Zdenek. Mobile Edge Computing: A Survey on Architecture and Computation Offloading[J]. IEEE Communications Surveys & Tutorials, 2017, 19(3): 1628-1656.
[4]	周娴玮, 龚启旭, 余松森. 基于Stackelberg博弈与深度强化学习的计算卸载策略[J]. 系统仿真学报, 2023, 35(2): 372-385.
	Zhou Xianwei, Gong Qixu, Yu Songsen. Computation Offloading Strategy Based on Stackelberg Game and DRL[J]. Journal of System Simulation, 2023, 35(2): 372-385.
[5]	Yang Song, Liu Jintian, Zhang Fei, et al. Caching-enabled Computation Offloading in Multi-region MEC Network via Deep Reinforcement Learning[J]. IEEE Internet of Things Journal, 2022, 9(21): 21086-21098.
[6]	Bi Suzhi, Huang Liang, Zhang Yingjun. Joint Optimization of Service Caching Placement and Computation Offloading in Mobile Edge Computing Systems[J]. IEEE Transactions on Wireless Communications, 2020, 19(7): 4947-4963.
[7]	Zhang Guanglin, Zhang Shun, Zhang Wenqian, et al. Joint Service Caching, Computation Offloading and Resource Allocation in Mobile Edge Computing Systems[J]. IEEE Transactions on Wireless Communications, 2021, 20(8): 5288-5300.
[8]	Zhao Gongming, Xu Hongli, Zhao Yangming, et al. Offloading Tasks with Dependency and Service Caching in Mobile Edge Computing[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(11): 2777-2792.
[9]	Zhou Ruiting, Wu Xiaoyi, Tan Haisheng, et al. Two Time-scale Joint Service Caching and Task Offloading for UAV-assisted Mobile Edge Computing[C]//IEEE INFOCOM 2022 - IEEE Conference on Computer Communications. Piscataway: IEEE, 2022: 1189-1198.
[10]	Wu Huaming, Chen Junqi, Nguyen T N, et al. Lyapunov-guided Delay-aware Energy Efficient Offloading in IIoT-MEC Systems[J]. IEEE Transactions on Industrial Informatics, 2023, 19(2): 2117-2128.
[11]	Xu Xiaolong, Liu Zhongjian, Bilal Muhammad, et al. Computation Offloading and Service Caching for Intelligent Transportation Systems with Digital Twin[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 20757-20772.
[12]	Huang Binbin, Liu Xiao, Xiang Yuanyuan, et al. Reinforcement Learning for Cost-effective IoT Service Caching at the Edge[J]. Journal of Parallel and Distributed Computing, 2022, 168(C): 120-136.
[13]	Wang Xiaofei, Wang Chenyang, Li Xiuhua, et al. Federated Deep Reinforcement Learning for Internet of Things with Decentralized Cooperative Edge Caching[J]. IEEE Internet of Things Journal, 2020, 7(10): 9441-9455.
[14]	Zhao Junhui, He Lin, Zhang Danyang, et al. A TP-DDPG Algorithm Based on Cache Assistance for Task Offloading in Urban Rail Transit[J]. IEEE Transactions on Vehicular Technology, 2023, 72(8): 10671-10681.
[15]	Zhou Tianqing, Xu Ming, Qin Dong, et al. Computing Offloading Based on TD3 Algorithm in Cache-assisted Vehicular NOMA-MEC Networks[J]. Sensors, 2023, 23(22): 9064.
[16]	Zhou Huan, Wang Zhenning, Zheng Hantong, et al. Cost Minimization-oriented Computation Offloading and Service Caching in Mobile Cloud-edge Computing: An A3C-based Approach[J]. IEEE Transactions on Network Science and Engineering, 2023, 10(3): 1326-1338.
[17]	Wei Yifei, Yu F R, Song Mei, et al. Joint Optimization of Caching, Computing, and Radio Resources for Fog-enabled IoT Using Natural Actor-critic Deep Reinforcement Learning[J]. IEEE Internet of Things Journal, 2019, 6(2): 2061-2073.
[18]	Yao Zhixiu, Xia Shichao, Li Yun, et al. Cooperative Task Offloading and Service Caching for Digital Twin Edge Networks: A Graph Attention Multi-agent Reinforcement Learning Approach[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(11): 3401-3413.
[19]	Dong Rui, She Changyang, Hardjawana W, et al. Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn from a Digital Twin[J]. IEEE Transactions on Wireless Communications, 2019, 18(10): 4692-4707.
[20]	Tang Fengxiao, Chen Xuehan, Tiago Koketsu Rodrigues, et al. Survey on Digital Twin Edge Networks (DITEN) Toward 6G[J]. IEEE Open Journal of the Communications Society, 2022, 3: 1360-1381.
[21]	Bøhn Eivind, Coates Erlend M, Moe Signe, et al. Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy optimization[C]//2019 International Conference on Unmanned Aircraft Systems (ICUAS). Piscataway: IEEE, 2019: 523-533.
[22]	黄思进, 文佳, 陈哲毅. 面向边缘车联网系统的智能服务迁移方法[J]. 系统仿真学报, 2025, 37(2): 379-391.
	Huang Sijin, Wen Jia, Chen Zheyi. Intelligent Service Migration Towards MEC-based IoV Systems[J]. Journal of System Simulation, 2025, 37(2): 379-391.
[23]	Barlacchi Gianni, Marco De Nadai, Larcher Roberto, et al. A Multi-source Dataset of Urban Life in the City of Milan and the Province of Trentino[J]. Scientific Data, 2015, 2: 150055.
[24]	Chen Zheyi, Zhang Junjie, Zheng Xianghan, et al. Profit-aware Cooperative Offloading in UAV-enabled MEC Systems Using Lightweight Deep Reinforcement Learning[J]. IEEE Internet of Things Journal, 2024, 11(12): 21325-21336.
[25]	Zhou Huan, Zhang Zhenyu, Wu Yuan, et al. Energy Efficient Joint Computation Offloading and Service Caching for Mobile Edge Computing: A Deep Reinforcement Learning Approach[J]. IEEE Transactions on Green Communications and Networking, 2023, 7(2): 950-961.
[26]	Huang Jiwei, Wan Jiangyuan, Bofeng Lü, et al. Joint Computation Offloading and Resource Allocation for Edge-cloud Collaboration in Internet of Vehicles via Deep Reinforcement Learning[J]. IEEE Systems Journal, 2023, 17(2): 2500-2511.

数字孪生云边网络下服务缓存与计算卸载优化

Optimization of Service Caching and Computation Offloading in Digital Twin Cloud-edge Networks

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 26

相关文章 15

编辑推荐

Metrics

本文评价

[1]	江明, 何韬. 基于深度强化学习的带容量约束车辆路径问题求解[J]. 系统仿真学报, 2025, 37(9): 2177-2187.
[2]	陆后军, 朱益飞, 荣延平, 张汪荟. 基于激光雷达的散货堆场数字孪生建模方法[J]. 系统仿真学报, 2025, 37(9): 2269-2286.
[3]	倪培龙, 毛鹏军, 王宁, 杨孟杰. 基于改进A-DDQN算法的机器人路径规划[J]. 系统仿真学报, 2025, 37(9): 2420-2430.
[4]	刘永奎, 杨康, 脱奔奔, 潘亚铎, 王欣宇, 王一涵, 龚永乾, 张霖, 王力翚, 林廷宇, 訾斌, 李元, 游玮, 徐旬. 数字孪生工业机器人：概念框架、关键技术与案例研究[J]. 系统仿真学报, 2025, 37(7): 1723-1752.
[5]	陈真, 吴卓屹, 张霖. 深度强化学习中策略表征研究简述[J]. 系统仿真学报, 2025, 37(7): 1753-1769.
[6]	刘涛, 李瀚熙, 尹勇, 刘佳仑. 航海智能仿真技术及应用研究综述[J]. 系统仿真学报, 2025, 37(7): 1684-1709.
[7]	陈清华, 梁作友, 关维娟, 季家东, 刘萍. 高低温试验箱数字孪生系统构建方法[J]. 系统仿真学报, 2025, 37(6): 1400-1411.
[8]	张文嘉, 张和明. 面向悬臂结构数字孪生体的灰盒模型构建方法研究[J]. 系统仿真学报, 2025, 37(5): 1158-1168.
[9]	伍国华, 曾家恒, 王得志, 郑龙, 邹伟. 基于深度强化学习的四旋翼航迹跟踪控制方法[J]. 系统仿真学报, 2025, 37(5): 1169-1187.
[10]	张会迈, 胡晓娅, 周纯杰. 面向TSN工控系统安全策略生成与优化的数字孪生框架[J]. 系统仿真学报, 2025, 37(4): 861-874.
[11]	张森, 代强强. 改进型深度确定性策略梯度的无人机路径规划[J]. 系统仿真学报, 2025, 37(4): 875-881.
[12]	李敏, 张森, 曾祥光, 王刚, 张童伟, 谢地杰, 任文哲, 张滔. 基于深度强化学习的四足机器人单腿越障轨迹规划[J]. 系统仿真学报, 2025, 37(4): 895-909.
[13]	王贺, 许佳宁, 闫广宇. 基于深度强化学习的AGV行人避让策略研究[J]. 系统仿真学报, 2025, 37(3): 595-606.
[14]	张斌, 雷永林, 李群, 高远, 陈永, 朱佳俊, 鲍琛龙. 基于强化学习的导弹突防决策建模研究[J]. 系统仿真学报, 2025, 37(3): 763-774.
[15]	江伦, 王大江, 孙文磊, 包胜辉, 刘涵, 常赛科. 基于数字孪生的变压器故障诊断方法研究[J]. 系统仿真学报, 2025, 37(3): 775-790.