计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200186-9.doi: 10.11896/jsjkx.230200186

• 网络&通信 • 上一篇    下一篇

车载边缘计算网络中基于MAB的动态任务卸载方案研究

薛建彬, 王海牛, 关向瑞, 郁柏文   

  1. 兰州理工大学 兰州 730050
  • 发布日期:2023-11-09
  • 通讯作者: 王海牛(wanghn0808@163.com)
  • 作者简介:(volvoxuejb@126.com)
  • 基金资助:
    甘肃省科技计划(23YFGA0062);甘肃省创新基金(2022A-215)

Study on Dynamic Task Offloading Scheme Based on MAB in Vehicular Edge Computing Network

XUE Jianbin, WANG Hainiu, GUAN Xiangrui, YU Bowen   

  1. Lanzhou University of Technology,Lanzhou 730050,China
  • Published:2023-11-09
  • About author:XUE Jianbin,born in 1973,Ph.D,associate professor.His main research intere-sts include wireless communication theo-ry and technology,mobile edge computing technology,etc.
    WANG Hainiu,born in 1997,postgra-duate.His main research interests include resource allocation,vehicular edge computing,and reinforcement learning.
  • Supported by:
    Gansu Science and Technology Program(23YFGA0062) and Innovation Fund of Gansu Province(2022A-215).

PDF (PC)

185

摘要： 将移动边缘计算技术应用到车载网络所形成的车载边缘计算系统,能够通过任务卸载为其他移动设备提供计算服务。然而,由于车载设备的移动性,导致了车载任务卸载环境是动态变化和不确定的,具有快速变化的网络拓扑、无线信道状态和计算负载,这些不确定性让任务卸载过程非理想化。针对这些不确定性,考虑将MEC服务器的计算资源下沉到车载设备,研究车辆之间的任务卸载,并提出了一种解决方案,使得车辆能够在未知状态信息的前提下学习周围车辆的服务性能并卸载任务。基于多臂老虎机框架,设计了一种二阶探索的强化学习算法,以最大化用户平均卸载回报,并且在一个卸载阶段结束后提出了一种服务集更新方式,以保证用户的服务质量。仿真结果表明,与现有的基于置信上限的算法相比,所提方案下的卸载回报提高了约34%。

关键词: 6G, 车载边缘计算, 多臂老虎机, 任务卸载, 强化学习

Abstract: The mobile edge computing system formed by applying mobile edge computing technology to Internet of Vehicles can provide computing services for other mobile devices through task offloading.However,due to the mobility of vehicle equipment,the environment of vehicular task offloading is dynamic and uncertain,with rapidly changing network topology,wireless channel state and computing load.These uncertainties make the task offloading process non-idealized.In view of these uncertainties,the computing resources of the MEC server are sunk into the vehicle equipment to study the task offloading between vehicles,and a solution is proposed to enable vehicles to learn the service performance of surrounding vehicles and offload tasks without knowing the status information.Based on the multi-arm bandits framework,a second-order exploration reinforcement learning algorithm is designed to maximize the average offloading return of users,and a service set update method is proposed after the end of an offloading phase to ensure the quality of service for users.Simulation results show that,compared with the existing algorithm based on upper confidence bound,the offloading return under the proposed scheme is improved by about 34%.

Key words: 6th generation mobile communication technology, Vehicular edge computing, Multi-armed bandit, Task offloading, Reinforcement learning

中图分类号: 

  • TN929.5
[1]QI W,LI Q,SONG Q,et al.Extensive edge intelligence for future vehicular networks in 6G[J].IEEE Wireless Communications,2021,28(4):128-135.
[2]KHAYYAT M,ELGENDY I A,MUTHANNAA,et al.Ad-vanced deep learning-based computational offloading for multilevel vehicular edge-cloud computing networks[J].IEEE Access,2020,8:137052-137062.
[3]KHAYYAT M,ALSHAHRANI A,ALHARBI S,et al.Multilevel service-provisioning-based autonomous vehicle applications[J].Sustainability,2020,12(6):2497.
[4]DINH T Q,TANG J,LA Q D,et al.Offloading in mobile edge computing:Task allocation and computational frequency scaling[J].IEEE Transactions on Communications,2017,65(8):3571-3584.
[5]SUN J,GU Q,ZHENGT,et al.Joint communication and computing resource allocation in vehicular edge computing[J].International Journal of Distributed Sensor Networks,2019,15(3):1550147719837859.
[6]HA K,PILLAI P,LEWIS G,et al.The impact of mobile multimedia applications on data center consolidation[C]//2013 IEEE International Conference on Cloud Engineering (IC2E).IEEE,2013:166-176.
[7]DAI Y,XU D,MAHARJAN S,et al.Joint offloading and resource allocation in vehicular edge computing and networks[C]//2018 IEEE Global Communications Conference (GLOBECOM).IEEE,2018:1-7.
[8]CHEN S,TAO Y,YU D,et al.Distributed learning dynamics of multi-armed bandits for edge intelligence[J].Journal of Systems Architecture,2021,114:101919.
[9]AUER P,CESA-BIANCHI N,FISCHER P.Finite-time analysis of the multiarmed bandit problem[J].Machine Learning,2002,47:235-256.
[10]CUI Y,LIANG Y,WANG R.Resource allocation algorithmwith multi-platform intelligent offloading in D2D-enabled vehi-cular networks[J].IEEE Access,2019,7:21246-21253.
[11]LI L,ZHOU H,XIONG S X,et al.Compound model of task arrivals and load-aware offloading for vehicular mobile edge computing networks[J].IEEE Access,2019,7:26631-26640.
[12]HAITAO Z,YI D,MENGKANG Z,et al.Multipath transmis-sion workload balancing optimization scheme based on mobile edge computing in vehicular heterogeneous network[J].IEEE Access,2019,7:116047-116055.
[13]DENG Z,CAI Z,LIANG M.A multi-hop VANETs-assisted offloading strategy in vehicular mobile edge computing[J].IEEE Access,2020,8:53062-53071.
[14]HUANG C M,LAI C F.The delay-constrained and network-situation-aware V2V2I VANET data offloading based on the multi-access edge computing(MEC) architecture[J].IEEE Open Journal of Vehicular Technology,2020,1:331-347.
[15]XUE J,HU Q,AN Y,et al.Joint task offloading and resource allocation in vehicle-assisted multi-access edge computing[J].Computer Communications,2021,177:77-85.
[16]SUN J,GU Q,ZHENG T,et al.Joint communication and computing resource allocation in vehicular edge computing[J].International Journal of Distributed Sensor Networks,2019,15(3):1550147719837859.
[17]HUANG X,YU R,XIE S,et al.Task-container matching game for computation offloading in vehicular edge computing and networks[J].IEEE Transactions on Intelligent Transportation Systems,2020,22(10):6242-6255.
[18]ZHANG Y,WANG C Y,WEI H Y.Parking reservation auction for parked vehicle assistance in vehicular fog computing[J].IEEE Transactions on Vehicular Technology,2019,68(4):3126-3139.
[19]HUANG X,YU R,YE D,et al.Efficient workload allocation and user-centric utility maximization for task scheduling in collaborative vehicular edge computing[J].IEEE Transactions on Vehicular Technology,2021,70(4):3773-3787.
[20]RAZA S,MIRZA M A,AHMAD S,et al.A vehicle to vehicle relay-based task offloading scheme in Vehicular Communication Networks[J].PeerJ Computer Science,2021,7:e486.
[21]BUDA S,GULENG S,WUC,et al.Collaborative vehicular edge computing towards greener ITS[J].IEEE Access,2020,8:63935-63944.
[22]CHA N,WU C,YOSHINAGAT,et al.Virtual edge:Exploring computation offloading in collaborative vehicular edge computing[J].IEEE Access,2021,9:37739-37751.
[23]BUTE M S,FAN P,ZHANG L,et al.An efficient distributed task offloading scheme for vehicular edge computing networks[J].IEEE Transactions on Vehicular Technology,2021,70(12):13149-13161.
[24]ZHANG X,ZHANG J,LIU Z,et al.MDP-based task offloading for vehicular edge computing under certain and uncertain transition probabilities[J].IEEE Transactions on Vehicular Techno-logy,2020,69(3):3296-3309.
[25]AUER P,CESA-BIANCHI N,FISCHER P.Finite-time analysis of the multiarmed bandit problem[J].Machine learning,2002,47(2):235-256.
[26]WU H,GUO X,LIU X.Adaptive exploration-exploitationtradeoff for opportunistic bandits[C]//International Conference on Machine Learning.PMLR,2018:5306-5314.
[27]SUN Y,GUO X,SONG J,et al.Adaptive learning-based task offloading for vehicular edge computing systems[J].IEEE Transactions on vehicular technology,2019,68(4):3061-3074.
[28]MAO Y,ZHANG J,SONG S H,et al.Stochastic joint radio and computational resource management for multi-user mobile-edge computing systems[J].IEEE Transactions on Wireless Communications,2017,16(9):5994-6009.
[29]GU X,ZHANG G,CAO Y.Cooperative mobile edge computing-cloud computing in Internet of vehicle:Architecture and energy-efficient workload allocation[J].Transactions on Emerging Telecommunications Technologies,2021,32(8):e4095.
[30]SALOMON A,AUDIBERT J Y,ALAOUI I E.Regret lowerbounds and extended Upper Confidence Bounds policies in stochastic multi-armed bandit problem[J].arXiv:1112.3827,2011.
[31]BUBECK S.Bandits games and clustering foundations[OL].Université des Sciences et Technologie de Lille-Lille I,2010.https://so1.cljtscd.com/scholar?q=Bandits+games+and+clustering+foundations.
[32]BUBECK S,CESA-BIANCHI N.Regret analysis of stochastic and nonstochastic multi-armed bandit problems[J].Foundations and Trends© in Machine Learning,2012,5(1):1-122.
[33]BNAYA Z,PUZIS R,STERNR,et al.Social network search as a volatile multi-armed bandit problem[J].Human,2013,2(2):84.
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