面向车联网自动驾驶的边缘智能多源数据处理

doi:10.13190/j.jbupt.2020-266

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (2): 102-108.doi: 10.13190/j.jbupt.2020-266

面向车联网自动驾驶的边缘智能多源数据处理

吕昕晨, 张晨宇

北京邮电大学移动互联网安全技术国家工程实验室, 北京 100876

收稿日期:2020-12-13 出版日期:2021-04-28 发布日期:2021-04-28
作者简介:吕昕晨(1992-),男,副研究员,E-mail:lvxinchen@bupt.edu.cn.
基金资助:
国家自然科学基金项目（62001048）；中央高校基本科研业务费-北邮新进教师项目（2020RC39）

Edge Intelligence Multi-Source Data Processing for Autonomous Driving in Internet of Vehicles

Lü Xin-chen, ZHANG Chen-yu

National Engineering Laboratory for Mobile Network Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-12-13 Online:2021-04-28 Published:2021-04-28

摘要/Abstract

摘要： 在车联网场景中，智能车辆受限于自身有限的感知范围和计算资源，难以实现高可靠性的自动驾驶.针对上述问题，提出了面向车联网自动驾驶的边缘智能多源数据处理方法，通过发掘网络中节点的空闲资源，提高系统的吞吐量，利用网络中的分布式数据，提高神经网络的推断准确率.为了解决车辆节点数据传输的耦合问题，构建了3层网络模型，对网络中的数据传输进行调度，并将原车辆节点一一映射为一个虚拟节点集合，对节点的数据传输进行解耦，从而把原问题转化为最小费用最大流的问题，实现了对自动驾驶网络计算、通信资源的高效分配.仿真结果表明，相比于本地处理的方案，所提方案可提升150%的系统吞吐量和12%的系统能效.

关键词: 边缘智能, 车联网, 多源数据处理, 网络流模型

Abstract: Designing a highly reliable automatic driving system is challenging due to the limited perception range and computing resources of intelligent vehicles. To this end, the distributed data and available resources in the network should be exploited. An edge intelligence multi-source data processing scheme for autonomous driving in Internet of vehicles is proposed. Firstly, a three-layer network model is constructed to schedule the data transmission. Then the original vehicle nodes are mapped one by one into a set of virtual nodes to decouple the data transmission. Thereafter, the original problem into a minimum cost maximum flow problem, realizing the efficient allocation of computing, communication resources in the network are transformed. Simulations show that the proposed scheme can improve system throughput by 150% and system energy efficiency by 12% compared with local processing scheme.

Key words: edge intelligence, Internet of vehicles, multi-source data processing, network flow model

中图分类号:

TP399

吕昕晨, 张晨宇. 面向车联网自动驾驶的边缘智能多源数据处理[J]. 北京邮电大学学报, 2021, 44(2): 102-108.

Lü Xin-chen, ZHANG Chen-yu. Edge Intelligence Multi-Source Data Processing for Autonomous Driving in Internet of Vehicles[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(2): 102-108.

参考文献

[1] Rao Q, Frtunikj J. Deep learning for self-driving cars:chances and challenges[C]//Proceedings of the 1st International Workshop on Software Engineering for AI in Autonomous Systems. New York:Association for Computing Machinery, 2018:35-38.
[2] Kavzoglu T. Increasing the accuracy of neural network classification using refined training data[J]. Environmental Modelling and Software, 2009, 24(7):850-858.
[3] 吴振铨, 叶东东, 余荣, 等. 车联网中基于停车协同的边缘计算卸载方法[J]. 北京邮电大学学报, 2019, 42(2):108-113. Wu Zhenquan, Ye Dongdong, Yu Rong, et al. Edge computing offloading with parked vehicular collaboration in Internet of vehicles[J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(2):108-113.
[4] Qiao Guanghua, Leng Supeng, Zhang Ke, et al. Collaborativetask offloading in vehicular edge multi-access networks[J]. IEEE Communications Magazine, 2018, 56(8):48-54.
[5] He Zongjian, Zhang Daqiang, Liang Junbin. Cost-efficient sensory data transmission in heterogeneous software-defined vehicular networks[J]. IEEE Sensors Journal, 2016, 16(20):7342-7354.
[6] Deng Shuiguang, Zhao Hailiang, Fang Weijia, et al. Edge intelligence:the confluence of edge computing and artificial intelligence[J]. IEEE Internet of Things Journal, 2020, 7(8):7457-7469.
[7] Zhao Yue, Li Meng, Lai Liangzhen, et al. Federated learning with non-IID data[EB/OL]. 2018(2018-06-02)[2020-12-03]. http://arxiv.org/abs/1806.00582arXiv:1806.00582.
[8] 李静林, 袁泉, 杨放春. 车联网群智感知与服务[J]. 中兴通讯技术, 2015, 21(6):6-9. Li Jinglin, Yuan Quan, Yang Fangchun. Crowd sensing and service in Internet of vehicles[J]. ZTE Technology Journal, 2015, 21(6):6-9.
[9] Benda D, Chu X, Sun S, et al. Renewable energy sharing among base stations as a min-cost-max-flow optimization problem[J]. IEEE Transactions on Green Communications and Networking, 2019, 3(1):67-78.
[10] Jiang D, Delgrossi L. IEEE 802.11 p:towards an international standard for wireless access in vehicular environments[C]//VTC Spring 2008-IEEE Vehicular Technology Conference. Piscataway:IEEE, 2008:2036-2040.

[1]	张佳敏帅莉莎董高雅阳小龙. 面向道路实况的车联网共享消息可信评估模型[J]. 北京邮电大学学报, 2023, 46(4): 40-45.
[2]	彭维平王戈宋成阎俊豪. 面向高移动性车联网场景的预测卸载决策算法[J]. 北京邮电大学学报, 2023, 46(2): 43-49.
[3]	刘琨王圆洁申自浩王辉刘沛骞. 结合区块链的车联网隐私保护可信预测缓存架构[J]. 北京邮电大学学报, 2022, 45(6): 145-150.
[4]	彭维平, 韩宁, 宋成. 边缘计算环境下无证书车联网身份认证方案[J]. 北京邮电大学学报, 2022, 45(1): 46-51.
[5]	皇甫伟, 杨心竹, 王欢, 胡晓彦. 基于出租车轨迹数据的车联网通信机会间隔模型[J]. 北京邮电大学学报, 2019, 42(3): 91-97.
[6]	吴振铨, 叶东东, 余荣, 周文辉, 何昭水. 车联网中基于停车协同的边缘计算卸载方法[J]. 北京邮电大学学报, 2019, 42(2): 108-113.
[7]	肖剑, 李文江, 耿洪杨, 翟英博. 车联网中可抵抗DoS攻击的RFID安全认证协议[J]. 北京邮电大学学报, 2019, 42(2): 114-119.
[8]	彭维平, 苏哲, 宋成, 贾宗璞. 面向车联网实时应用场景的任务卸载决策算法[J]. 北京邮电大学学报, 2018, 41(4): 44-50.
[9]	刘宴兵, 宋秀丽, 肖永刚. 车联网认证机制和信任模型[J]. 北京邮电大学学报, 2017, 40(3): 1-18.
[10]	侯蓉晖, 郭素霞. 车联网场景中时延受限内容传输方案[J]. 北京邮电大学学报, 2017, 40(3): 85-90.
[11]	王剑, 张子键, 袁坚. 应用于CAN总线的广播认证系统[J]. 北京邮电大学学报, 2015, 38(4): 24-28.
[12]	黄晓敏, 汪洋, 张继良, 张乃通. 车联网无线链路传输数据业务性能评估[J]. 北京邮电大学学报, 2014, 37(s1): 66-71.
[13]	李静林, 刘志晗, 杨放春. 车联网体系结构及其关键技术[J]. 北京邮电大学学报, 2014, 37(6): 95-100.
[14]	张志群,丁炜,武穆清. TCP/IP拥塞控制机制在MPLS网络中的#br# 改进及分析[J]. 北京邮电大学学报, 2002, 25(2): 93-97.

面向车联网自动驾驶的边缘智能多源数据处理

Edge Intelligence Multi-Source Data Processing for Autonomous Driving in Internet of Vehicles

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价