大规模无线通信网络移动边缘计算和缓存研究

doi:10.11959/j.issn.1000-436x.2021096

通信学报 ›› 2021, Vol. 42 ›› Issue (4): 44-61.doi: 10.11959/j.issn.1000-436x.2021096

所属专题：边缘计算

• 专题：面向未来移动网络的大规模组网关键技术 • 上一篇下一篇

大规模无线通信网络移动边缘计算和缓存研究

黄永明¹^,², 郑冲¹, 张征明¹, 尤肖虎¹^,²

¹ 东南大学信息科学与工程学院，江苏南京 210096
² 紫金山实验室，江苏南京 211111

修回日期:2021-03-31 出版日期:2021-04-25 发布日期:2021-04-01
作者简介:黄永明（1977- ），男，江苏吴江人，博士，东南大学教授、博士生导师，主要研究方向为智能 5G/6G 移动通信、毫米波无线通信等。
郑冲（1994- ），男，湖北荆州人，东南大学博士生，主要研究方向为智能无线通信、移动边缘计算、边缘智能、物联网、深度强化学习和联邦学习等。
张征明（1994- ），男，安徽阜阳人，东南大学博士生，主要研究方向为无线大数据、机器学习、5G移动网络、无人机辅助通信和资源管理等。
尤肖虎（1962- ），男，山东济宁人，博士，东南大学教授、博士生导师，主要研究方向为移动通信系统和信号处理及其应用等。
基金资助:
国家自然科学基金资助项目(61720106003);国家重点研发计划基金资助项目(2018YFB1800801)

Research on mobile edge computing and caching in massive wireless communication network

Yongming HUANG¹^,², Chong ZHENG¹, Zhengming ZHANG¹, Xiaohu YOU¹^,²

¹ School of Information Science and Engineering, Southeast University, Nanjing 210096, China
² Purple Mountain Laboratory, Nanjing 211111, China

Revised:2021-03-31 Online:2021-04-25 Published:2021-04-01
Supported by:
The National Natural Science Foundation of China(61720106003);The National Key Research and Devel-opment Program of China(2018YFB1800801)

摘要/Abstract

摘要：

面向未来6G移动通信的大规模网络移动边缘计算与缓存技术，首先，介绍了大规模无线网络下移动边缘计算和缓存的架构与原理，并阐释了移动边缘计算和缓存技术在大规模无线网络中的必要性和普适性。接着，从计算卸载、边缘缓存、多维资源分配、用户关联和隐私保护这5个关键问题出发，综述和分析了移动边缘计算和缓存赋能大规模无线网络时会引入的新型关键问题以及对应的解决方案研究，并进一步指出了未来的发展趋势和研究方向。最后，针对隐私保护问题，提出了一种基于联邦学习的隐私保护方案，并通过仿真结果表明所提方案能够同时保护用户数据隐私且改善系统服务质量。

关键词: 大规模无线网络, 移动边缘计算, 缓存, 隐私保护, 联邦学习

Abstract:

For the large-scale network mobile edge computing and caching technology of future 6G mobile communications, firstly, the architectures and principles of mobile edge computing and caching in large-scale wireless networks were introduced, and the necessity and universality were clarified.Then, from the perspective of the five key issues in the mobile edge computing and caching enabled large-scale wireless network, including computing offloading, edge caching, multi-dimensional resource allocation, user association and privacy protection, the recent researches and further pointed out the future development trends and research directions were reviewed and analyzed.Finally, for the privacy preservation issue, a federated learning based privacy-preserving scheme was proposed.Simulation results show that the proposed scheme can simultaneously preserve user privacy and improve the quality of service.

Key words: massive wireless network, mobile edge computing, caching, privacy protection, federated learning

中图分类号:

TN92

黄永明, 郑冲, 张征明, 尤肖虎. 大规模无线通信网络移动边缘计算和缓存研究[J]. 通信学报, 2021, 42(4): 44-61.

Yongming HUANG, Chong ZHENG, Zhengming ZHANG, Xiaohu YOU. Research on mobile edge computing and caching in massive wireless communication network[J]. Journal on Communications, 2021, 42(4): 44-61.

图/表 10

图1

图2

图3

图4

表1

MEC赋能大规模网络中关键问题和解决方案的分析与总结"

关键问题	关键研究点	相关文献	方法论
	能耗敏感型计算卸载	文献[15-16]	整体卸载，基于SCA的迭代优化的卸载
计算卸载问题			部分卸载，基于阈值优先级的计算卸载
	时延敏感型计算卸载	文献[17]	基于Lyapunov的低复杂度在线动态计算卸载
	时延-能耗敏感型计算卸载	文献[18-19]	基于惩罚函数和D.C.规划的迭代搜索计算卸载
			基于交替凸搜索的计算卸载
			基于统计用户请求的历史数据
	非编码缓存	文献[21-26]	基于优化算法
边缘缓存问题			基于动态规划和强化学习
边缘缓存问题			基于深度神经网的PDA设计
	编码缓存	文献[20,27-30]	基于强化学习的缓存更新和多播调度
			基于优化算法
	计算资源分配	文献[31-32]	时间维度的资源分配，基于Lyapunov的最优计算资源分配
			空间维度的资源分配，基于势博弈论的计算资源分配
	缓存资源分配	文献[33-34]	基于用户社交关系的静态缓存资源配置
多维资源分配问题			基于用户时变内容请求的在线响应式动态缓存资源分配
多维资源分配问题	能量资源分配	文献[35-36]	CSI和TSI知识完备时，基于凸优化的离线传输功率分配算法实；CSI和TSI知识仅因果已知，基于启发式的在线传输功率分配
			基于拉格朗日对偶法的离线能耗优化算法；基于滑动窗口以及序列优化的在线传输功率分配算法
	通信资源分配	文献[37]	基于回声状态网络和迁移学习的上下行传输资源块动态分配
	混合资源分配	文献[38-39]	基于深度强化学习的通信与计算资源联合分配
			基于自适应优化算法、粒子群算法与Pareto一对一匹配算法相结合的计算、能量和通信资源混合资源分配
用户关联问题	基于时延最小化用户关联	文献[40]	基于深度强化学习的自适应用户关联算法，实现任务总计算时延最小化
	基于能耗最小化用户关联	文献[41]	基于最短路径优化的用户关联算法，实现时延约束下的能效最大化
			基于粒子群的用户关联，实现时延能耗联合代价最小化
	基于能耗?时延权衡用户关联	文献[42-44]	基于0-1整数规划的迭代优化用户关联，实现时延能耗联合定义的QoE代价最小化
			基于模拟退火的用户关联，实现用户QoE最大化
			基于Markov决策的策略迭代算法来保护用户位置隐私的同时实现最优业务迁移决策
	用户位置隐私保护	文献[50-52]	基于chaff的保护策略来对抗窃听者，保护用户位置隐私
隐私保护问题			基于图学习来保护用户位置隐私的同时实现基本的业务提供
隐私保护问题			深度强化学习联合区块链授权与认证的用户数据加密技术，实现安全的内容缓存服务
	用户数据隐私保护	文献[53-56]	博弈论联合中国余数论的内容加密协议，实现用户数据隐私保护下的多归属访问缓存业务
			基于概率论的公钥加密技术，实现数据隐私保护下的用户排名查询业务基于混沌系统的伪随机置换加密技术

表1

图5

图6

图7

表2

2种方案在不同用户数上的性能对比"

方案	总用户数					测试集准确率
方案	总用户数	λ=0.990	λ=0.991	λ=0.992	λ=0.993	λ=0.994	λ=0.995	λ=0.996	λ=0.997	λ=0.998	λ=0.999
FL无缓存							78.47%
	400
FL有缓存		79.68%	79.05%	79.19%	80.40%	79.62%	80.78%	79.7%	$78 . 84 %$	80.11%	78.84%
FL无缓存							77.36%
	500
FL有缓存		77.70%	$78 . 84 %$	77.64%	76.65%	77.77%	78.05%	77.92%	78.70%	77.30%	78.03%

表2

图8

参考文献 59

[1]	YOU X H , WANG C X , HUANG J ,et al. Towards 6G wireless communication networks:vision,enabling technologies,and new paradigm shifts[J]. Science China Information Sciences, 2020,64(1): 1-74.
[2]	CISCO. Cisco visual networking index:global mobile data traffic forecast update,2017–2022[R]. Cisco Public Information, 2017.
[3]	HE S W , HUANG W , WANG J H ,et al. Cache-enabled coordinated mobile edge network:opportunities and challenges[J]. IEEE Wireless Communications, 2020,27(2): 204-211.
[4]	GUO H Z , LIU J J , ZHANG J . Computation offloading for multi-access mobile edge computing in ultra-dense networks[J]. IEEE Communications Magazine, 2018,56(8): 14-19.
[5]	KAMEL M , HAMOUDA W , YOUSSEF A . Ultra-dense networks:a survey[J]. IEEE Communications Surveys ＆ Tutorials, 2016,18(4): 2522-2545.
[6]	ABBAS N , ZHANG Y , TAHERKORDI A ,et al. Mobile edge computing:a survey[J]. IEEE Internet of Things Journal, 2018,5(1): 450-465.
[7]	谢人超, 廉晓飞, 贾庆民 ,等. 移动边缘计算卸载技术综述[J]. 通信学报, 2018,39(11): 138-155.
	XIE R C , LIAN X F , JIA Q M ,et al. Survey on computation offloading in mobile edge computing[J]. Journal on Communications, 2018,39(11): 138-155.
[8]	ZHANG K , LENG S P , HE Y J ,et al. Mobile edge computing and networking for green and low-latency Internet of things[J]. IEEE Communications Magazine, 2018,56(5): 39-45.
[9]	PAN C H , ELKASHLAN M , WANG J Z ,et al. User-centric C-RAN architecture for ultra-dense 5G networks:challenges and methodologies[J]. IEEE Communications Magazine, 2018,56(6): 14-20.
[10]	TIAN X J , JIA W J . Improved clustering and resource allocation for ultra-dense networks[J]. China Communications, 2020,17(2): 220-231.
[11]	ETSI. ETSI GS MEC 002.Mobile edge computing (MEC); technical requirements[R]. ETSI White Paper, 2016.
[12]	代玥玥 . 移动边缘计算中资源管理问题的研究[D]. 成都:电子科技大学, 2019.
	DAI Y Y . Research on resource management problems in mobile edge computing[D]. Chengdu:University of Electronic Science and Technology of China, 2019.
[13]	ZENG J , SUN J Y , WU B W ,et al. Mobile edge communications,computing,and caching (MEC3) technology in the maritime communication network[J]. China Communications, 2020,17(5): 223-234.
[14]	HE Y , YU F R , ZHAO N ,et al. Secure social networks in 5G systems with mobile edge computing,caching,and device-to-device communications[J]. IEEE Wireless Communications, 2018,25(3): 103-109.
[15]	HABER E E , NGUYEN T M , ASSI C ,et al. An energy-efficient task offloading solution for MEC-based IoT in Ultra-dense networks[C]// 2019 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE Press, 2019: 1-7.
[16]	YOU C S , HUANG K B . Multiuser resource allocation for mobile-edge computation offloading[C]// 2016 IEEE Global Communications Conference. Piscataway:IEEE Press, 2016: 1-6.
[17]	MAO Y Y , ZHANG J , LETAIEF K B . Dynamic computation offloading for mobile-edge computing with energy harvesting devices[J]. IEEE Journal on Selected Areas in Communications, 2016,34(12): 3590-3605.
[18]	ZHANG J , HU X P , NING Z L ,et al. Energy-latency tradeoff for energy-aware offloading in mobile edge computing networks[J]. IEEE Internet of Things Journal, 2018,5(4): 2633-2645.
[19]	QIN M , CHENG N , JING Z W ,et al. Service-oriented energy-latency tradeoff for IoT task partial offloading in MEC-enhanced multi-RAT networks[J]. IEEE Internet of Things Journal, 2021,8(3): 1896-1907.
[20]	MADDAH-ALI M A , NIESEN U . Fundamental limits of caching[J]. IEEE Transactions on Information Theory, 2014,60(5): 1077-1081.
[21]	BORST S C , GUPTA V , WALID A . Distributed caching algorithms for content distribution networks[C]// IEEE Conference on Information Communications. Piscataway:IEEE Press, 2010: 1-9.
[22]	TAMOOR-UL-HASSAN S , BENNIS M , NARDELLI P H J ,et al. Caching in wireless small cell networks:a storage-bandwidth tradeoff[J]. IEEE Communications Letters, 2016,20(6): 1175-1178.
[23]	ZHU K L , ZHI W T , CHEN X ,et al. Socially motivated data caching in ultra-dense small cell networks[J]. IEEE Network, 2017,31(4): 42-48.
[24]	DAI C , ZHU K , WANG R ,et al. Contextual multi-armed bandit for cache-aware decoupled multiple association in UDNs:a deep learning approach[J]. IEEE Transactions on Cognitive Communications and Networking, 2019,5(4): 1046-1059.
[25]	TANG J , DAI T W , CUI M M ,et al. Optimization for maximizing sum secrecy rate in SWIPT-enabled NOMA systems[J]. IEEE Access, 2018,6: 43440-43449.
[26]	ZHANG Z M , YANG Y Q , HUA M ,et al. Proactive caching for vehicular multi-view 3D video streaming via deep reinforcement learning[J]. IEEE Transactions on Wireless Communications, 2019,18(5): 2693-2706.
[27]	KARAMCHANDANI N , NIESEN U , MADDAH-ALI M A ,et al. Hierarchical coded caching[J]. IEEE Transactions on Information Theory, 2016,62(6): 3212-3229.
[28]	JI M Y , CAIRE G , MOLISCH A F . Fundamental limits of caching in wireless D2D networks[J]. IEEE Transactions on Information Theory, 2016,62(2): 849-869.
[29]	YAN Q F , CHENG M Q , TANG X H ,et al. On the placement delivery array design for centralized coded caching scheme[J]. IEEE Transactions on Information Theory, 2017,63(9): 5821-5833.
[30]	ZHANG Z M , CHEN H Y , HUA M ,et al. Double coded caching in ultra dense networks:caching and multicast scheduling via deep reinforcement learning[J]. IEEE Transactions on Communications, 2020,68(2): 1071-1086.
[31]	YANG X , CHEN Z Y , LI K K ,et al. Communication-constrained mobile edge computing systems for wireless virtual reality:scheduling and tradeoff[J]. IEEE Access, 2018,6: 16665-16677.
[32]	LIU H , JIA H M , CHEN J Q ,et al. Computing resource allocation of mobile edge computing networks based on potential game theory[C]// 2018 IEEE 4th International Conference on Computer and Communications. Piscataway:IEEE Press, 2018: 693-699.
[33]	NIKOLAOU S , RENESSE R V , SCHIPER N . Proactive cache placement on cooperative client caches for online social networks[J]. IEEE Transactions on Parallel and Distributed Systems, 2016,27(4): 1174-1186.
[34]	AZIMI S M , SIMEONE O , SENGUPTA A ,et al. Online edge caching and wireless delivery in fog-aided networks with dynamic content popularity[J]. IEEE Journal on Selected Areas in Communications, 2018,36(6): 1189-1202.
[35]	WANG F , XU J , CUI S G . Optimal energy allocation and task offloading policy for wireless powered mobile edge computing systems[J]. IEEE Transactions on Wireless Communications, 2020,19(4): 2443-2459.
[36]	WANG F , XING H , XU J . Real-time resource allocation for wireless powered multiuser mobile edge computing with energy and task causality[J]. IEEE Transactions on Communications, 2020,68(11): 7140-7155.
[37]	CHEN M Z , SAAD W , YIN C C ,et al. Data correlation-aware resource management in wireless virtual reality (VR):an echo state transfer learning approach[J]. IEEE Transactions on Communications, 2019,67(6): 4267-4280.
[38]	WANG F , XING H , XU J . Real-time resource allocation for wireless powered multiuser mobile edge computing with energy and task causality[J]. IEEE Transactions on Communications, 2020,68(11): 7140-7155.
[39]	DIAO X B , ZHENG J C , WU Y ,et al. Joint computing resource,power,and channel allocations for D2D-assisted and NOMA-based mobile edge computing[J]. IEEE Access, 2019,7: 9243-9257.
[40]	HO T M , NGUYEN K K . Joint server selection,cooperative offloading and handover in multi-access edge computing wireless network:A deep reinforcement learning approach[J]. IEEE Transactions on Mobile Computing, 2020,PP(99): 1536-1233.
[41]	THANANJEYAN S , CHAN C A , WONG E ,et al. Mobility-aware energy optimization in hosts selection for computation offloading in multi-access edge computing[J]. IEEE Open Journal of the Communications Society, 2020,1: 1056-1065.
[42]	MA S Y , SONG S D , ZHAO J M ,et al. Joint network selection and service placement based on particle swarm optimization for multi-access edge computing[J]. IEEE Access, 2020,8: 160871-160881.
[43]	ZHAO J M , WU W J , GUO X ,et al. Access selection considering mobile edge computing in ultra dense network[C]// 2017 3rd IEEE International Conference on Computer and Communications. Piscataway:IEEE Press, 2017: 433-437.
[44]	GAO Y , WU W J , ZHOU T Q ,et al. QoE-aware access node selection considering mobile edge computing[C]// 2018 IEEE 4th International Conference on Computer and Communications. Piscataway:IEEE Press, 2018: 1914-1918.
[45]	SAAD W , HAN Z , DEBBAH M ,et al. Coalitional game theory for communication networks[J]. IEEE Signal Processing Magazine, 2009,26(5): 77-97.
[46]	ZHENG C , LIU S H , HUANG Y M ,et al. MEC-enabled wireless VR video service:a learning-based mixed strategy for energy-latency tradeoff[C]// 2020 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE Press, 2020: 1-6.
[47]	ABDILDIN Y G , ABBAS A E . An algorithm for excluding redundant assessments in a multiattribute utility problem[J]. Procedia Computer Science, 2012,9(1): 802-811.
[48]	张佳乐, 赵彦超, 陈兵 ,等. 边缘计算数据安全与隐私保护研究综述[J]. 通信学报, 2018,39(3): 1-21.
	ZHANG J L , ZHAO Y C , CHEN B ,et al. Survey on data security and privacy-preserving for the research of edge computing[J]. Journal on Communications, 2018,39(3): 1-21.
[49]	TIAN Z H , WANG Y H , SUN Y B ,et al. Location privacy challenges in mobile edge computing:classification and exploration[J]. IEEE Network, 2020,34(2): 52-56.
[50]	WANG W X , GE S X , ZHOU X B . Location-privacy-aware service migration in mobile edge computing[C]// 2020 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE Press, 2020: 1-6.
[51]	HE T , CIFTCIOGLU E N , WANG S Q ,et al. Location privacy in mobile edge clouds:a chaff-based approach[J]. IEEE Journal on Selected Areas in Communications, 2017,35(11): 2625-2636.
[52]	WU Q , CHEN X , ZHOU Z ,et al. Mobile social data learning for user-centric location prediction with application in mobile edge service migration[J]. IEEE Internet of Things Journal, 2019,6(5): 7737-7747.
[53]	DAI Y Y , XU D , ZHANG K ,et al. Deep reinforcement learning and permissioned blockchain for content caching in vehicular edge computing and networks[J]. IEEE Transactions on Vehicular Technology, 2020,69(4): 4312-4324.
[54]	XU Q C , SU Z , ZHENG Q H ,et al. Game theoretical secure caching scheme in multihoming edge computing-enabled heterogeneous networks[J]. IEEE Internet of Things Journal, 2019,6(3): 4536-4546.
[55]	PASUPULETI S K , RAMALINGAM S , BUYYA R . An efficient and secure privacy-preserving approach for outsourced data of resource constrained mobile devices in cloud computing[J]. Journal of Network and Computer Applications, 2016,64: 12-22.
[56]	BAHRAMI M , SINGHAL M . A light-weight permutation based method for data privacy in mobile cloud computing[C]// 2015 3rd IEEE International Conference on Mobile Cloud Computing,Services,and Engineering. Piscataway:IEEE Press, 2015: 189-198.
[57]	KRIZHEVSKY A , HINTON G . Learning multiple layers of features from tiny images[R]. Handbook of Systemic Autoimmune Diseases,(2009-01-04)[2021-01-21].
[58]	KAMP M , ADILOVA L , SICKING J ,et al. Efficient decentralized deep learning by dynamic model averaging[C]// Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin:Springer, 2018: 393-409.
[59]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.

大规模无线通信网络移动边缘计算和缓存研究

Research on mobile edge computing and caching in massive wireless communication network

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 59

相关文章 15

Metrics

推荐阅读 0

[1]	杨龙, 赵丽, 周雨晨, 贺冰涛, 陈健. 缓存辅助的协作NOMA携能传输[J]. 通信学报, 2023, 44(6): 77-89.
[2]	马鑫迪, 李清华, 姜奇, 马卓, 高胜, 田有亮, 马建峰. 面向Non-IID数据的拜占庭鲁棒联邦学习[J]. 通信学报, 2023, 44(6): 138-153.
[3]	金彪, 李逸康, 姚志强, 陈瑜霖, 熊金波. GenFedRL：面向深度强化学习智能体的通用联邦强化学习框架[J]. 通信学报, 2023, 44(6): 183-197.
[4]	李开菊, 许强, 王豪. 冗余数据去除的联邦学习高效通信方法[J]. 通信学报, 2023, 44(5): 79-93.
[5]	余晟兴, 陈泽凯, 陈钟, 刘西蒙. DAGUARD：联邦学习下的分布式后门攻击防御方案[J]. 通信学报, 2023, 44(5): 110-122.
[6]	姜慧, 何天流, 刘敏, 孙胜, 王煜炜. 面向异构流式数据的高性能联邦持续学习算法[J]. 通信学报, 2023, 44(5): 123-136.
[7]	田有亮, 吴柿红, 李沓, 王林冬, 周骅. 基于激励机制的联邦学习优化算法[J]. 通信学报, 2023, 44(5): 169-180.
[8]	张佳乐, 朱诚诚, 孙小兵, 陈兵. 基于GAN的联邦学习成员推理攻击与防御方法[J]. 通信学报, 2023, 44(5): 193-205.
[9]	冯涛, 陈李秋, 方君丽, 石建明. 基于本地化差分隐私和属性基可搜索加密的区块链数据共享方案[J]. 通信学报, 2023, 44(5): 224-233.
[10]	夏莹杰, 朱思雨, 刘雪娇. 区块链架构下具有条件隐私的车辆编队跨信任域高效群组认证研究[J]. 通信学报, 2023, 44(4): 111-123.
[11]	苏新, 张桂福, 行鸿彦, Zenghui Wang. 基于平衡生成对抗网络的海洋气象传感网入侵检测研究[J]. 通信学报, 2023, 44(4): 124-136.
[12]	胡柏吉, 张晓娟, 李元诚, 赖荣鑫. 支持多功能的V2G网络隐私保护数据聚合方案[J]. 通信学报, 2023, 44(4): 187-200.
[13]	余雪勇, 邱礼翔, 宋家宁, 朱洪波. 无人机辅助边缘计算中安全通信与能效优化策略[J]. 通信学报, 2023, 44(3): 45-54.
[14]	徐明, 张保俊, 伍益明, 应晨铎, 郑宁. 面向网络攻击和隐私保护的多智能体系统分布式共识算法[J]. 通信学报, 2023, 44(3): 117-127.
[15]	范伟, 彭诚, 朱大立, 王雨晴. 移动边缘计算网络下基于静态贝叶斯博弈的入侵响应策略研究[J]. 通信学报, 2023, 44(2): 70-81.