西安邮电大学电子工程学院;西安市物联网泛在工程创新联合体;
针对车辆边缘计算(Vehicular Edge Computing, VEC)卸载与资源分配过程中由于边缘服务器资源受限导致的时延增大的问题,提出一种基于深度强化学习的计算卸载与资源分配(Compute Offload and Resource Allocation Based on Deep Q-Netwrk, CORADQN)算法。构建VEC网络架构,通过拆分计算密集型车载任务及利用空闲服务车辆的计算资源,将计算任务分别卸载至边缘服务器、空闲服务车辆和本地车辆进行处理,以降低VEC网络系统的总时延。将计算卸载与资源分配转化为多约束优化问题,并将平均奖励作为样本的优先级进行采样,从而提高样本的利用率,加快算法收敛速度。仿真结果表明,相较于完全本地(ALL-Local)算法、完全边缘(ALL-Edge)算法、联邦卸载(Federated Offloading Scheme, FOS)算法及深度Q学习(Deep Q-Network, DQN)算法,所提算法能够最小化VEC网络的系统时延。
571 | 1 | 99 |
下载次数 | 被引频次 | 阅读次数 |
[2] WANG J,FENG D,ZHANG S,et al.Computation offloading for mobile edge computing enabled vehicular networks[J].IEEE Access,2019,7:62624-62632.
[3] GOUMIDI H,ALIOUAT Z,HAROUS S.Vehicular cloud computing security:A survey[J].Arabian Journal for Science and Engineering,2020,45(4):2473-2499.
[4] KHAN R,KUMAR P,JAYAKODY D,et al.A survey on security and privacy of 5G technologies:Potential solutions recent advancements,and future directions[J].IEEE Communications Surveys & Tutorials,2019,22(1):196-248.
[5] SABIREEN H,NEELANARAYANAN V.A review on fog computing:Architecture,fog with IoT,algorithms and research challenges[J].Ict Express,2021,7(2):162-176.
[6] ZHANG K,MAO Y,LENG S,et al.Contract-theoretic approach for delay constrained offloading in vehicular edge computing networks[J].Mobile Networks and Applications,2019,24:1003-1014.
[7] MEKKI T,JABRI I,RACHEDI A,et al.Towards multi-access edge based vehicular fog computing architecture[C]//Proceeding of the 2018 IEEE Global Communications Conference (GLOBECOM).Abu Dhabi:IEEE,2018:1-6.
[8] LIU L,CHEN C,PEI Q,et al.Vehicular edge computing and networking:A survey[J].Mobile Networks and Applications,2021,26:1145-1168.
[9] LIU Y,WANG S,HUANG J,et al.A computation offloading algorithm based on game theory for vehicular edge networks[C]//Proceeding of the 2018 IEEE International Conference on Communications (ICC).Sheraton Kansas:IEEE,2018:1-6.
[10] ZHANG D Y,TANG J Z,DU W T,et al.Joint optimization of computation offloading and UL/DL resource allocation in MEC systems[C]//Proceeding of the 2018 IEEE 29th Annual International Symposium on Personal,Indoor and Mobile Radio Communications (PIMRC).IEEE:Bologna,2018:1-6.
[11] SHI J,DU J,WANG J,et al.Distributed V2V computation offloading based on dynamic pricing using deep reinforcement learning[C]//Proceeding of the 2020 IEEE Wireless Communication and Network Conference (WCNC).Seoul Korea:IEEE,2020:1-6.
[12] SUN Y,GUO X,ZHOU J,et al.Adaptive learning-based task offloading for vehicular edge computing systems[C]//Proceeding of the 2019 IEEE Transactions on Vehicular Technology.[S.l]:IEEE,2019:3061-3074.
[13] WANG M,WANG J,GAO Z,et al.Game theory based opportunistic computation offloading in cloud-enabled IoV[C]//Proceeding of the 2019 IEEE Access.[S.I]:IEEE,2019:32551-32561.
[14] WANG H,LI X,JI H,et al.Federated offloading scheme to minimize latency in MEC-enabled vehicular networks[C]//Proceeding of the 2018 IEEE Globecom Workshops (GCWkshps).Abu Dhabi:IEEE,2018:1-6.
[15] CHEN C,WANG Z,PEI Q,et al.Distributed computation offloading using deep reinforcement learning in internet of vehicles[C]//Proceeding of the 2020 IEEE International Conference on Communications in China (ICC).Chongqing:IEEE,2020:823-828.
[16] 林峰,罗铖文,丁鹏举,等.车联网中自适应联合计算卸载资源分配算法[J].计算机工程与设计,2021,42(7):1824-1830.LIN F,LUO C W,DING P J,et al.Resource allocation algorithm for adaptive joint computing offloading in C-V2X[J].Computer Engineering and Design,2021,42(7):1824-1830.(in Chinese)
[17] ZHENG X,ZHANG L,YAN L.CTSVM:A robust twin support vector machine with correntropy-induced loss function for binary classification problems[J].Information Sciences,2021,559:22-45.
[18] MUSTAPHA A,MOHAMED L,ALI K,et al.An overview of gradient descent algorithm optimization in machine learning:Application in the ophthalmology field[C]//Proceeding of the 2020 Communications in Computer and Information Science.[S.l]:Springer Cham,2020,1207:349-359.
[19] KANG C,RONG C,REN W,et al.Deep deterministic policy gradient based on double network prioritized experience replay[J].IEEE Access,2021,9:60296-60308.
[20] 陈鑫,兰凤崇,陈吉清.基于改进深度强化学习的自动泊车路径规划[J].重庆理工大学学报(自然科学),2021,35(7):17-27.CHEN X,LAN F C,CHEN J Q.Deep reinforcement learning based trajectory planning for automatic parking[J].Journal of Chongqing University of Technology(Natural Science),2021,35(7):17-27.(in Chinese)
[21] YANG X,YU X,HUANG H,et al.Energy efficiency based joint computation offloading and resource allocation in multi-access MEC systems[J].IEEE Access,2019(7):117054-117062.
基本信息:
DOI:10.13682/j.issn.2095-6533.2024.04.004
中图分类号:TP18;TN929.5;U495
引用信息:
[1]师亚莉,肖春艳,王宇等.车联网中基于深度强化学习的计算卸载与资源分配算法[J].西安邮电大学学报,2024,29(04):30-38.DOI:10.13682/j.issn.2095-6533.2024.04.004.
基金信息:
陕西省重点研发计划项目(2022GY-055)