计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 240100103-9.doi: 10.11896/jsjkx.240100103

• 网络&通信 • 上一篇    下一篇

边缘计算网络中基于排队论的通信和计算资源联合优化

薛建彬, 郁柏文, 徐小凤, 豆俊   

  1. 兰州理工大学计算机与通信学院 兰州 730050
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 郁柏文(13639329628@163.com)
  • 作者简介:(volvoxuejb@126.com)
  • 基金资助:
    甘肃省科技资助计划(23YFGA0062);基于5G移动边缘计算的无人机应急场景中绿色通信方案研究(2022A-215)

Queueing Theory-based Joint Optimization of Communication and Computing Resources in Edge Computing Networks

XUE Jianbin, YU Bowen, XU Xiaofeng, DOU Jun   

  1. School of Computer and Communication,Lanzhou University of Technology,Lanzhou 730053,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:XUE Jianbin,born in 1973,Ph.D,associate professor.His main research intere-sts include wireless communication theory and technology,mobile edge computing technology,etc.
    YU Bowen,born in 1998,postgraduate.His main research interests include edge computing resource allocation and automatic driving of vehicles queuing up on the Internet of Vehicles.
  • Supported by:
    Gansu Provincial Science and Technology Program Funding(23YFGA0062) and Research on Green Communication Scheme in UAV Emergency Scenarios Based on 5G Mobile Edge Computing(2022A-215).

PDF (PC)

153

摘要： 高可靠和低延迟是目前车联网边缘计算网络中最重要的研究方向之一。为了满足车联网网络中复杂多变的任务请求,有效并且高效地分配通信资源和计算资源,提出了一种基于任务排队论模型和边缘计算模型相结合的智能通信和计算资源分配的多目标强化学习策略。该策略将通信资源和计算资源的分配相结合,以降低由延迟和可靠性组成的系统总成本。该策略可以被分解成3种算法,首先联合计算卸载与协作算法是该策略的一个通用框架,它首先使用KNN方法为生成的任务请求选择卸载层,如边缘计算层和本地计算层;然后,当选择本地计算层执行任务时,使用称为协作车辆选择的算法来查找执行协作计算的目标车辆;最后,通信和计算资源的分配被定义为两个独立的目标,称为多目标资源分配的算法在移动边缘计算层使用强化学习来实现问题的最优解。仿真结果表明,与随机计算、全部边缘计算和全部本地计算相比,所提策略有效地降低了系统的总成本。KNN方法和随机卸载方法相比,节省了系统的总成本,强化学习算法在系统总成本的控制上也优于传统的粒子群算法。

关键词: 车联网, 边缘计算, 排队论, KNN, 资源分配, 强化学习

Abstract: High reliability and low latency is one of the most important research directions in edge computing networks for vehi-cular networking.In order to meet the complex and variable task requests in vehicular networking networks,communication and computation resources are allocated effectively and efficiently.A multi-objective reinforcement learning strategy for intelligent communication and computation resource allocation based on the combination of task queuing theory model and edge computing model is proposed.The strategy combines the allocation of communication and computation resources to reduce the total system cost consisting of latency and reliability.The strategy can be decomposed into three algorithms,firstly,the joint computational offloading and collaboration algorithm is a generic framework for the strategy which first selects the offloading layer for the generated task requests such as the edge computing layer and the local computing layer using the KNN method.Then,when the local computing layer is selected to perform the task,an algorithm called collaborative vehicle selection is used to find the target vehicle to perform the collaborative computation.Finally,the allocation of communication and computational resources is defined as two independent objectives and the algorithm called multi-objective resource allocation uses reinforcement learning at the mobile edge computing layer to achieve an optimal solution to the problem.Simulation results show that the proposed strategy effectively reduces the total cost of the system compared to random computing,all edge computing and all local computing.The KNN approach saves the total cost of the system compared to the random offloading approach and the reinforcement learning algorithm outperforms the traditional particle swarm algorithm in controlling the total cost of the system.

Key words: Internet of Vehicles, Edge computing, Queueing theory, KNN, Resource allocation, Reinforcement learning

中图分类号: 

  • TN929.5
[1]ELAYOUBI S E,BROWN P,DEGHEL M,et al.Radio resource allocation and retransmission schemes for URLLC over 5G networks[J].IEEE Journal on Selected Areas in Communications,2019,37(4):896-904.
[2]NI Y,HE J,CAI L,et al.Delay analysis and messagedelivery strategy in hybrid V2I/V2V networks[C]//2016 IEEE Global Communications Conference(GLOBECOM).IEEE,2016:1-6.
[3]MAO Y,YOU C,ZHANG J,et al.A survey on mobile edgecomputing:The communication perspective[J].IEEE Communications Surveys & Tutorials,2017,19(4):2322-2358.
[4]HOU X,LI Y,CHEN M,et al.Vehicular fog computing:A viewpoint of vehicles as the infrastructures[J].IEEE Transactions on Vehicular Technology,2016,65(6):3860-3873.
[5]XIE R,TANG Q,WANG Q,et al.Collaborative vehicular edge computing networks:Architecture design and research challenges[J].IEEE Access,2019,7:178942-178952.
[6]JIA M,CAO J,LIANG W.Optimal cloudlet placement and user to cloudlet allocation in wireless metropolitan area networks[J].IEEE Transactions on Cloud Computing,2015,5(4):725-737.
[7]WANG Y,TAO X,ZHANG X,et al.Cooperative task offloa-ding in three-tier mobile computing networks:An ADMM framework[J].IEEE Transactions on Vehicular Technology,2019,68(3):2763-2776.
[8]YE H,LIANG L,LI G Y,et al.Machine learning for vehicularnetworks:Recent advances and application examples[J].IEEE Vehicular Technology Magazine,2018,13(2):94-101.
[9]LUO C,JI J,WANG Q,et al.Channel state information prediction for 5G wireless communications:A deep learning approach[J].IEEE Transactions on Network Science and Engineering,2018,7(1):227-236.
[10]WANG R,YANG H,WANG H,et al.Social overlapping com-munity-aware neighbor discovery for D2D communications[J].IEEE Wireless Communications,2016,23(4):28-34.
[11]WANG R,LIU H,WANG H,et al.Distributed security architecture based on blockchain for connected health:Architecture,challenges,and approaches[J].IEEE Wireless Communications,2019,26(6):30-36.
[12]ASHRAF M I,LIU C F,BENNIS M,et al.Dynamic resource allocation for optimized latency and reliability in vehicular networks[J].IEEE Access,2018,6:63843-63858.
[13]FENG L,LI W,LIN Y,et al.Joint computation offloading and URLLC resource allocation for collaborative MEC assisted cellular-V2X networks[J].IEEE Access,2020,8:24914-24926.
[14]WANG J,ZHAO L,LIU J,et al.Smart resource allocation formobile edge computing:A deep reinforcement learning approach[J].IEEE Transactions on emerging topics in computing,2019,9(3):1529-1541.
[15]WANG Y,LANG P,TIAN D,et al.A game-based computation offloading method in vehicular multiaccess edge computing networks[J].IEEE Internet of Things Journal,2020,7(6):4987-4996.
[16]KIEN VU T,BENNIS M,DEBBAH M,et al.Ultra-ReliableCommunication in 5G mmWave Networks:A Risk-Sensitive Approach[J].arXiv:1802.03878,2018.
[17]BATEWELA S,LIU C F,BENNIS M,et al.Risk-sensitive task fetching and offloading for vehicular edge computing[J].IEEE Communications Letters,2019,24(3):617-621.
[18]XU Y,GUI G,GACANIN H,et al.A Survey on Resource Allo-cation for 5G Heterogeneous Networks:Current Research,Future Trends,and Challenges[J].IEEE Communications Surveys and Tutorials,2021,23(2):668-695.
[19]SUN W,STRÖM E G,BRÄNNSTRÖM F,et al.Radio resource management for D2D-based V2V communication[J].IEEE Transactions on Vehicular Technology,2015,65(8):6636-6650.
[20]VU T K,LIU C F,BENNIS M,et al.Ultra-reliable and low latency communication in mmWave-enabled massive MIMO networks[J].IEEE Communications Letters,2017,21(9):2041-2044.
[21]LIU C F,BENNIS M,DEBBAH M,et al.Dynamic task offloading and resource allocation for ultra-reliable low-latency edge computing[J].IEEE Transactions on Communications,2019,67(6):4132-4150.
[22]KHERRAF N,SHARAFEDDINE S,ASSI C M,et al.Latency and reliability-aware workload assignment in IoT networks with mobile edge clouds[J].IEEE Transactions on Network and Service Management,2019,16(4):1435-1449.
[23]GHANEM W R,JAMALI V,SUN Y,et al.Resource allocation for multi-user downlink MISO OFDMA-URLLC systems[J].IEEE Transactions on Communications,2020,68(11):7184-7200.
[24]YANG H,ZHANG K,ZHENG K,et al.Joint frame design and resource allocation for ultra-reliable and low-latency vehicular networks[J].IEEE Transactions on Wireless Communications,2020,19(5):3607-3622.
[25]LIN C C,DENG D J,YAOC C.Resource allocation in vehicular cloud computing systems with heterogeneous vehicles and roadside units[J].IEEE Internet of Things Journal,2017,5(5):3692-3700.
[26]REN S,HE Y.COCA:Online distributed resource management for cost minimization and carbon neutrality in data centers[C]//Proceedings of the International Conference on High Perfor-mance Computing,Networking,Storage and Analysis.2013:1-12.
[27]JIANG Z,MAO S.Energy delay tradeoff in cloud offloading for multi-core mobile devices[J].IEEE Access,2015,3:2306-2316.
[28]LI T,ZHOU H,LUO H,et al.Modeling software defined satellite networks using queueing theory[C]//2017 IEEE International Conference on Communications(ICC).IEEE,2017:1-6.
[29]SHEN Y H,CAO J,CHEN X J.Cost optimization problem incommunication systems based on queuing theory [J].Applied Mathematics,2007(S1):95-98.
[30]WANG W B,YE Q W,ZHOU Y,et al.A dynamic load balancing algorithm based on queuing theory comprehensive index evaluation [J].Telecommunications Science,2018,34(7):86-91.
[31]WU W,HU Z,SONG Y.A new method for OPF combining interior point method and filled function method[C]//2016 IEEE Power and Energy Society General Meeting(PESGM).IEEE,2016:1-5.
[32]YANG Y,MA Y,XIANG W,et al.Joint optimization of energy consumption and packet scheduling for mobile edge computing in cyber-physical networks[J].IEEE Access,2018,6:15576-15586.
[33]BOBARSHAD H,SHIKH-BAHAEI M.M/M/1 queuing model for adaptive cross-layer error protection in WLANs[C]//2009 IEEE Wireless Communications and Networking Conference.IEEE,2009:1-6.
[34]MA X,WANG S,ZHANG S,et al.Cost-efficient resource provi-sioning for dynamic requests in cloud assisted mobile edge computing[J].IEEE Transactions on Cloud Computing,2019,9(3):968-980.
[35]XU Y,XIE H,HU R Q.Max-min beamforming design for he-terogeneous networks with hardware impairments[J].IEEE Communications Letters,2020,25(4):1328-1332.
[36]XU Y,GUI G.Optimal resource allocation for wireless powered multi-carrier backscatter communication networks[J].IEEE Wireless Communications Letters,2020,9(8):1191-1195.
[37]SUTTON R S,BARTOA G.Reinforcement learning:An introduction[M].MIT press,2018.
[38]XIA Y,WU L,WANG Z,et al.Cluster-enabled cooperativescheduling based on reinforcement learning for high-mobility vehicular networks[J].IEEE Transactions on Vehicular Techno-logy,2020,69(11):12664-12678.
[39]ZHOU Y,TANG F,KAWAMOTO Y,et al.Reinforcementlearning-based radio resource control in 5G vehicular network[J].IEEE Wireless Communications Letters,2019,9(5):611-614.
[40]LIANG H,ZHANG X,ZHANG J,et al.A novel adaptive re-source allocation model based on SMDP and reinforcement learning algorithm in vehicular cloud system[J].IEEE Transactions on Vehicular Technology,2019,68(10):10018-10029.
[41]LEE S,LEE S K.Resource allocation for vehicular fog computingusing reinforcement learning combined with heuristic information[J].IEEE Internet of Things Journal,2020,7(10):10450-10464.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发