智能网联汽车计算卸载与边缘缓存联合优化策略

doi:10.16182/j.issn1004731x.joss.22-0147

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (6): 1203-1214.doi: 10.16182/j.issn1004731x.joss.22-0147

智能网联汽车计算卸载与边缘缓存联合优化策略

丁飞¹^,²^,³(), 沙宇晨¹^,²(), 洪莹¹^,², 蒯晓¹^,², 张登银¹^,²^,³

^1.南京邮电大学物联网学院, 江苏南京 210003
^2.南京邮电大学江苏省宽带无线通信和物联网重点实验室, 江苏南京 210003
^3.南京邮电大学通信与网络技术国家工程研究中心, 江苏南京 210003

收稿日期:2022-03-01 修回日期:2022-04-25 出版日期:2023-06-29 发布日期:2023-06-20
通讯作者: 沙宇晨 E-mail:dingfei@njupt.edu.cn;554320330@qq.com
作者简介:丁飞(1981-)，男，副教授，博士，研究方向为物联网与信息系统、边缘智能与协同计算等。E-mail：dingfei@njupt.edu.cn
基金资助:
国家自然科学基金(61871446);江苏省重点研发计划(BE2020084-1);江苏省“六大人才高峰”高层次人才培养(DZXX-008);中国博士后科学基金面上资助项目(2019M661900);江苏省博士后科研资助计划(2019K026)

Joint Optimization Strategy of Computing Offloading and Edge Caching for Intelligent Connected Vehicles

Fei Ding¹^,²^,³(), Yuchen Sha¹^,²(), Ying Hong¹^,², Xiao Kuai¹^,², Dengyin Zhang¹^,²^,³

^1.School of Internet of things, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
^2.Key Laboratory of Broadband Wireless Communication and Internet of Things of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
^3.National Engineering Research Center for Communication and Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Received:2022-03-01 Revised:2022-04-25 Online:2023-06-29 Published:2023-06-20
Contact: Yuchen Sha E-mail:dingfei@njupt.edu.cn;554320330@qq.com

摘要/Abstract

摘要：

为了保障智能网联汽车的低时延通信，利用蜂窝车联网中V2X(vehicle to everything)信道模型、边缘计算技术，研究计算卸载与边缘缓存联合优化策略。设计了一种智能网联汽车计算卸载与边缘缓存协同模型L-DDPG(least-deep deterministic policy gradient)，通过对车载本地与边缘计算资源的整合，支持V2X场景下对不同计算任务的分类处理。由边缘平台对车载计算请求进行预判决，确保对连续的计算任务快速响应；结合基于最近最少使用(least recently used, LRU)的边缘缓存策略，实现对新计算任务的高效管理；基于DDPG算法对计算卸载与边缘缓存进行联合卸载决策。仿真结果表明：L-DDPG模型性能优于传统模型，能够有效提升系统的工作效能，在保障业务服务质量的同时降低时延和系统资源消耗。

关键词: 智能网联汽车, V2X(vehicle to everything), 多接入边缘计算, 深度强化学习, 计算卸载, 边缘缓存

Abstract:

To guarantee the low-delay communication of intelligent connected vehicles, the V2X channel model and the multi-access edge computing (MEC) technology, are used to carry out the research of the joint optimization strategy of computing offloading and edge caching. An intelligent connected vehicle with task offloading and edge caching model least-deep deterministic policy gradient(L-DDPG) is developed. By integrating the vehicular local and edge computing resources, the classification processing of different computing tasks in V2X scenarios is supported. The vehicular computing request is prejudged by edge platform to ensure the rapid response of continuous homogeneous computing tasks. Combining with the least recently used strategy, the new computing tasks are efficiently managed. A joint offloading decision for computing offloading and edge caching is carried out based on deep deterministic policy gradient(DDPG) algorithm. Simulation results show that the performance of L-DDPG model is better than that of traditional models, which can effectively improve the system performance, ensure the service quality, and reduce the time delay and resource consumption.

Key words: intelligent connected vehicle, vehicle to everything(V2X), multi-access edge computing, deep reinforcement learning, computing offloading, edge caching

中图分类号:

TP393

丁飞, 沙宇晨, 洪莹, 蒯晓, 张登银. 智能网联汽车计算卸载与边缘缓存联合优化策略[J]. 系统仿真学报, 2023, 35(6): 1203-1214.

Fei Ding, Yuchen Sha, Ying Hong, Xiao Kuai, Dengyin Zhang. Joint Optimization Strategy of Computing Offloading and Edge Caching for Intelligent Connected Vehicles[J]. Journal of System Simulation, 2023, 35(6): 1203-1214.

图/表 10

图1

图2

图3

表1

仿真参数

参数	数值
RSU覆盖半径/m	300
车辆发射功率 $p v / d B m$	20
CPU能耗功率 $p c / W$	5
路侧边缘节点数	[3, 7]
单个MEC节点的计算能力 $f i m / G H z$	[5, 9]
上行传输信道数量 $K$	10
信道总带宽 $B / M H z$	20
高斯白噪声功率 $σ 2 / d B m$	-100
车辆计算能力 $f i v / G H z$	1
计算任务大小 $d i / M B$	20
权重因子 $α$	0.5
缓存空间 $H m / M B$	500
最大容忍时延 $t i m a x / s$	0.003
载波频率 $f c / G H z$	5.915
基站的高度 $h B S / m$	35
车辆的高度 $h U T / m$	1.5
发送信号功率 $P t x / d B m$	23
天线增益 $G a n t e n n a / d B i$	3
噪声功率 $P n o i s e / W$	$3 × 10 - 13$

表1

图4

图5

图6

图7

图8

图9

参考文献 29

1	王君, 纪晓东, 张欣然, 等. 5G蜂窝车联网组网性能研究[J]. 电信科学, 2020, 36(1): 49-57.
	Wang Jun, Ji Xiaodong, Zhang Xinran, et al. Performance Evaluation of 5G Cellular Vehicle Networks[J]. Telecommunications Science, 2020, 36(1): 49-57.
2	European Telecommunications Standards Institute. ETSI GS MEC 002, Mobile Edge Computing(MEC); Technical Requirements: V1.1.1 [S]. Valbonne-sophia Antipolis France: European Telecommunications Standards Institute, 2016.
3	European Telecommunications Standards Institute. ETSI GS MEC 001, Mobile Edge Computing(MEC); Terminology: V1.1.1 [S]. Valbonne-sophia Antipolis France: European Telecommunications Standards Institute, 2016.
4	European Telecommunications Standards Institute. ETSI GS MEC-IEG 004, Mobile Edge Computing(MEC); Service Scenarios: V1.1.1 [S]. Valbonne-Sophia Antipolis France: European Telecommunications Standards Institute, 2015.
5	European Telecommunications Standards Institute. ETSI GS MEC 009, Mobile Edge Computing (MEC); General principles for Mobile Edge Service APIs: V1.1.1 [S]. Valbonne-sophia Antipolis France: European Telecommunications Standards Institute, 2017.
6	European Telecommunications Standards Institute. ETSI GS MEC 011, Mobile Edge Computing(MEC); Mobile Edge Platform Application Enablement: V1.1.1 [S]. Valbonne-sophia Antipolis France: European Telecommunications Standards Institute, 2017.
7	Zhang Ke, Mao Yuming, Leng Supeng, et al. Optimal Delay Constrained Offloading for Vehicular Edge Computing Networks[C]//2017 IEEE International Conference on Communications(ICC). Piscataway, NJ, USA: IEEE, 2017: 1-6.
8	Liu Yujiong, Wang Shangguang, Huang Jie, et al. A Computation Offloading Algorithm Based on Game Theory for Vehicular Edge Networks[C]//2018 IEEE International Conference on Communications(ICC). Piscataway, NJ, USA: IEEE, 2018: 1-6.
9	Wang Hansong, Li Xi, Ji Hong, et al. Federated Offloading Scheme to Minimize Latency in MEC-Enabled Vehicular Networks[C]//2018 IEEE Globecom Workshops(GC Wkshps). Piscataway, NJ, USA: IEEE, 2018: 1-6.
10	张海波, 荆昆仑, 刘开健, 等. 车联网中一种基于软件定义网络与移动边缘计算的卸载策略[J]. 电子与信息学报, 2020, 42(3): 645-652.
	Zhang Haibo, Jing Kunlun, Liu Kaijian, et al. An Offloading Mechanism Based on Software Defined Network and Mobile Edge Computing in Vehicular Networks[J]. Journal of Electronics & Information Technology, 2020, 42(3): 645-652.
11	张海波, 王子心, 贺晓帆. SDN和MEC架构下V2X卸载与资源分配[J]. 通信学报, 2020, 41(1): 114-124.
	Zhang Haibo, Wang zi Xin, He Xiaofan. V2X Offloading and Resource Allocation Under SDN and MEC Architecture[J]. Journal on Communications, 2020, 41(1): 114-124.
12	Huang Xumin, Yu Rong, Kang Jiawen, et al. Distributed Reputation Management for Secure and Efficient Vehicular Edge Computing and Networks[J]. IEEE Access, 2017, 5: 25408-25420.
13	黄永明, 郑冲, 张征明, 等. 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.
	Huang Yongming, Zheng Chong, Zhang Zhengming, et al. Research on Mobile Edge Computing and Caching in Massive Wireless Communication Network[J]. Journal on Communications, 2021, 42(4): 44-61.
14	Ji Hongjing, Alfarraj O, Tolba A. Artificial Intelligence-empowered Edge of Vehicles: Architecture, Enabling Technologies, and Applications[J]. IEEE Access, 2020, 8: 61020-61034.
15	兰巨龙, 王鹏, 申涓, 等. 大规模接入汇聚网络的抵近式缓存技术研究[J]. 物联网学报, 2017, 1(1): 50-54.
	Lan Julong, Wang Peng, Shen Juan, et al. Research on Push Cache of Large-scale Converging Access Networks[J]. Chinese Journal on Internet of Things, 2017, 1(1): 50-54.
16	El Haber E, Nguyen T M, Assi C. Joint Optimization of Computational Cost and Devices Energy for Task Offloading in Multi-tier Edge-clouds[J]. IEEE Transactions on Communications, 2019, 67(5): 3407-3421.
17	Zhang Ni, Guo Songtao, Dong Yifan, et al. Joint Task Offloading and Data Caching in Mobile Edge Computing Networks[J]. Computer Networks, 2020, 182: 107446.
18	Ko S W, Han Kaifeng, Huang Kaibin. Wireless Networks for Mobile Edge Computing: Spatial Modeling and Latency Analysis[J]. IEEE Transactions on Wireless Communications, 2018, 17(8): 5225-5240.
19	Ebrahimzadeh A, Maier M. Cooperative Computation Offloading in FiWi Enhanced 4G HetNets Using Self-organizing MEC[J]. IEEE Transactions on Wireless Communications, 2020, 19(7): 4480-4493.
20	Deng Maofei, Tian Hui, Xinchen Lü. Adaptive Sequential Offloading Game for Multi-cell Mobile Edge Computing[C]//2016 23rd International Conference on Telecommunications(ICT). Piscataway, NJ, USA: IEEE, 2016: 1-5.
21	Li Yongfu, Chen Wenbo, Peeta S, et al. Platoon Control of Connected Multi-vehicle Systems under V2X Communications: Design and Experiments[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(5): 1891-1902.
22	The Alliance for Telecommunications Industry Solutions. ATIS.3GPP.37.885.V1530, Study on Evaluation Methodology of New Vehicle-to-everything (V2X) Use Cases for LTE and NR [S]. Washington, DC, US: ATIS, 2019.
23	3rd Generation Partnership Project. TR 38.901, Study on Channel Model for Frequencies from 0.5 to 100 GHz: V14.0.0 [S]. Valbonne-sophia Antipolis France: 3rd Generation Partnership Project, 2017.
24	刘雷, 陈晨, 冯杰, 等. 车载边缘计算中任务卸载和服务缓存的联合智能优化[J]. 通信学报, 2021, 42(1): 18-26.
	Liu Lei, Chen Chen, Feng Jie, et al. Joint Intelligent Optimization of Task Offloading and Service Caching for Vehicular Edge Computing[J]. Journal on Communications, 2021, 42(1): 18-26.
25	Li S L, Du J B, Zhai D S, et al. Task Offloading, Load Balancing, and Resource Allocation in MEC Networks[J]. IET Communications, 2020, 14(9): 1451-1458.
26	Meng Hao, Chao Daichong, Huo Ru, et al. Deep Reinforcement Learning Based Delay-sensitive Task Scheduling and Resource Management Algorithm for Multi-User Mobile-edge Computing Systems[C]//Proceedings of the 2019 4th International Conference on Mathematics and Artificial Intelligence. New York, NY, USA: Association for Computing Machinery, 2019: 66-70.
27	Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous Control with Deep Reinforcement Learning[C]//4th International Conference on Learning Representations, ICLR 2016. New York, USA: ICLR, 2016: 1-14.
28	Ye Junhong, Zhang Yingjun. DRAG: Deep Reinforcement Learning Based Base Station Activation in Heterogeneous Networks[J]. IEEE Transactions on Mobile Computing, 2020, 19(9): 2076-2087.
29	Tong Minglei, Wang Xiaoxiang, Wang Yulong, et al. Computation Offloading Scheme with D2D for MEC-enabled Cellular Networks[C]//2020 IEEE/CIC International Conference on Communications in China(ICCC Workshops). Piscataway, NJ, USA: IEEE, 2020: 111-116.

[1]	赵传超, 郑睿, 龚莉, 马小陆. 网联环境中新能源货车的粒子群调度方法[J]. 系统仿真学报, 2023, 35(6): 1337-1350.
[2]	戴宇轩, 崔承刚. 基于深度强化学习的Boost变换器控制策略[J]. 系统仿真学报, 2023, 35(5): 1109-1119.
[3]	徐浩添, 秦龙, 曾俊杰, 胡越, 张琪. 基于深度强化学习的对手建模方法研究综述[J]. 系统仿真学报, 2023, 35(4): 671-694.
[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.
[5]	史佳洁, 杨鹏, 皮雁南. 基于机器学习的地铁行人流在线优化控制研究[J]. 系统仿真学报, 2023, 35(2): 386-395.
[6]	张森, 张孟炎, 邵敬平, 普杰信. 基于随机策略搜索的多机三维路径规划方法[J]. 系统仿真学报, 2022, 34(6): 1286-1295.
[7]	倪凌佳, 黄晓霞, 李红旮, 张子博. 基于协作式深度强化学习的火灾应急疏散仿真研究[J]. 系统仿真学报, 2022, 34(6): 1353-1366.
[8]	蒋阳升, 王思琛, 高宽, 刘梦, 姚志洪. 混入智能网联车队的混合交通流元胞自动机模型[J]. 系统仿真学报, 2022, 34(5): 1025-1032.
[9]	王红微, 杨鹏. 基于深度强化学习的机场货运业务优化研究[J]. 系统仿真学报, 2022, 34(3): 651-660.
[10]	李启锐, 彭心怡. 基于深度强化学习的云作业调度及仿真研究[J]. 系统仿真学报, 2022, 34(2): 258-268.
[11]	李长云, 黎建波, 徐曦, 李亭立. 具有能量收集设备的移动边缘计算资源分配研究[J]. 系统仿真学报, 2022, 34(11): 2313-2322.
[12]	高昂, 董志明, 张国辉, 梁涛, 郭齐胜. LVC训练系统中计算机生成兵力生成技术研究[J]. 系统仿真学报, 2021, 33(3): 745-752.
[13]	曾贲, 房霄, 孔德帅, 宋祥祥, 贾政轩, 林廷宇. 一种数据驱动的对抗博弈智能体建模方法[J]. 系统仿真学报, 2021, 33(12): 2838-2845.

智能网联汽车计算卸载与边缘缓存联合优化策略

Joint Optimization Strategy of Computing Offloading and Edge Caching for Intelligent Connected Vehicles

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 29

相关文章 13

编辑推荐

Metrics

本文评价