基于数字孪生的城市交通流智能预测与导引策略

doi:10.11959/j.issn.1000-0801.2023047

电信科学 ›› 2023, Vol. 39 ›› Issue (3): 70-79.doi: 10.11959/j.issn.1000-0801.2023047

基于数字孪生的城市交通流智能预测与导引策略

廖熙雯, 冷甦鹏, 明昱君, 李天扬

电子科技大学信息与通信工程学院，四川成都 611731

修回日期:2023-03-09 出版日期:2023-03-20 发布日期:2023-03-01
作者简介:廖熙雯（1998- ），女，电子科技大学信息与通信工程学院博士生，主要研究方向为无线通信、交通路网与车联网协同优化
冷甦鹏（1973- ），男，电子科技大学教授、博士生导师，主要研究方向为物联网、车联网、新一代宽带无线网络、无线自组织网、智能交通信息系统的资源管理、介质访问控制、路由、组网与互联、智能算法理论及技术应用等
明昱君（1999- ），女，电子科技大学信息与通信工程学院硕士生，主要研究方向为无线网络及智能优化、交通路网与车联网
李天扬（1997- ），女，电子科技大学信息与通信工程学院博士生，主要研究方向为无人机网络
基金资助:
国家重点研发计划项目(2018YFE0117500);国家自然科学基金资助项目(62171104)

Digital twin based intelligent urban traffic forecasting and guidance strategy

Xiwen LIAO, Supeng LENG, Yujun MING, Tianyang LI

School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China

Revised:2023-03-09 Online:2023-03-20 Published:2023-03-01
Supported by:
The National Key Research and Development Program of China(2018YFE0117500);The National Natural Science Foundation of China(62171104)

摘要/Abstract

摘要：

物联网和人工智能等信息技术的快速发展极大地推动了交通系统的变革，同样也带来了机遇与挑战。针对现有导航系统忽略交通流时空特征而产生的策略重复性拥堵问题，对宏观交通流和微观车辆驾驶分别建模，并挖掘其耦合关系，进而提出一种基于数字孪生的城市智能交通流分层预测与导引策略，为减缓交通拥堵提供新思路。在该策略中，虚拟空间中的上层道路孪生通过扩散卷积递归神经网络预测时空交通流量，并显式作用于车辆路径规划决策。在此基础上，提出一种时空协同深度强化学习方法，用于实现车辆面向未来的协作式路径规划，指导虚拟空间中的下层车辆孪生选出最优策略反馈于真实世界。基于SUMO仿真平台进行了仿真验证。实验结果表明，本文所提方法在提高出行达成率、缓解拥堵等方面显著优于现有算法，能够有效提升城市交通出行效率。

关键词: 数字孪生, 交通拥堵, 深度强化学习, 交通流预测与导引, 扩散卷积

Abstract:

As the technology of ubiquitous Internet of things and artificial intelligence improves by leaps and bounds, the transportation system revolution is flourishing and bringing new opportunities and challenges.Considering the defect in the existing navigation system, and the neglect of the temporal and spatial characteristics of traffic flow, the macro traffic network and micro vehicle network were modeled and their coupling relationship was mined.Then, a digital twin based urban traffic forecasting and guidance method was proposed to alleviate the problem of traffic congestion.The spatial-temporal traffic flow information was predicted through the diffusion convolution recurrent neural network, which was explicitly applied to the vehicle path planning decision.On this basis, a spatial-temporal collaborative deep reinforcement learning method was proposed to implement the future-oriented collaborative path planning of vehicles.It also guided the underlying vehicle twins to select the optimal strategy for the real world.With SUMO for simulation verification, the experimental results show that the proposed method is significantly better than the existing algorithms in improving the travel completion ratio and congestion relief, and can improve the efficiency of urban traffic travel.

Key words: digital twin, traffic congestion, deep reinforcement learning, traffic flow forecasting and guidance, diffu-sion convolution

廖熙雯, 冷甦鹏, 明昱君, 李天扬. 基于数字孪生的城市交通流智能预测与导引策略[J]. 电信科学, 2023, 39(3): 70-79.

Xiwen LIAO, Supeng LENG, Yujun MING, Tianyang LI. Digital twin based intelligent urban traffic forecasting and guidance strategy[J]. Telecommunications Science, 2023, 39(3): 70-79.

图/表 8

图1

图2

图3

表1

图4

图5

图6

图7

参考文献 22

[1]	齐旭 . 车路协同系统：解决交通拥堵是目的[N]. 中国电子报, 2021-10-01(7).
	QI X . Vehicle-road collaboration system:solving traffic congestion is the goal[N]. China Electronics News, 2021-10-01(7).
[2]	RAHIMI-FARAHANI H , RASSAFI A A , MIRBAHA B . Forced-node route guidance system:incorporating both user equilibrium and system optimal benefits[J]. IET Intelligent Transport Systems, 2019,13(12): 1851-1859.
[3]	LI Y , YU R , SHAHABI C ,et al. Diffusion convolutional recurrent neural network:Data-driven traffic forecasting[J]. arXiv preprint arXiv:1707.01926, 2017.
[4]	GUO S N , LIN Y F , FENG N ,et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]// Proceedings of the AAAI Conference on Artificial Intelligence[S.l.:s.n.], 2019: 922-929.
[5]	JIANG M R , CHEN W , LI X . S-GCN-GRU-NN:a novel hybrid model by combining a spatiotemporal graph convolutional network and a gated recurrent units neural network for short-term traffic speed forecasting[J]. Journal of Data,Information and Management, 2021,3(1): 1-20.
[6]	PIASCIK R , VICKERS J , LOWRY D ,et al. Technology area 12:materials,structures,mechanical systems,and manufacturing road map[J]. NASA Office of Chief Technologist, 2010: 15-88.
[7]	BRUNNER P , DENK F , HUBER W ,et al. Virtual safety performance assessment for automated driving in complex urban traffic scenarios[C]// Proceedings of 2019 IEEE Intelligent Transportation Systems Conference (ITSC). Piscataway:IEEE Press, 2019: 679-685.
[8]	HU C , FAN W C , ZENG E ,et al. Digital twin-assisted real-time traffic data prediction method for 5g-enabled Internet of vehicles[J]. IEEE Transactions on Industrial Informatics, 2022,18(4): 2811-2819.
[9]	ALAM K M , EL SADDIK A . C2PS:a digital twin architecture reference model for the cloud-based cyber-physical systems[J]. IEEE Access, 2017(5): 2050-2062.
[10]	DU W J , ZHANG T F , ZHANG G G ,et al. A digital twin framework and an implementation method for urban rail transit[C]// Proceedings of 2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing). Piscataway:IEEE Press, 2021: 1-4.
[11]	ZHAO L , HAN G J , LI Z H ,et al. Intelligent digital twin-based software-defined vehicular networks[J]. IEEE Network, 2020,34(5): 178-184.
[12]	PAN Y H , WU N Q , QU T ,et al. Digital-twin-driven production logistics synchronization system for vehicle routing problems with pick-up and delivery in industrial park[J]. International Journal of Computer Integrated Manufacturing, 2021,34(7/8): 814-828.
[13]	曹佳钰, 冷甦鹏, 张科 . 面向自动驾驶应用的车联多智能体信息融合协同决策机制研究[J]. 物联网学报, 2020,4(3): 69-77.
	CAO J Y , LENG S P , ZHANG K . Multi-agent driven collaborative decision mechanism of information fusion for autonomous driving vehicles[J]. Chinese Journal on Internet of Things, 2020,4(3): 69-77.
[14]	詹全 . 闭环数字孪生智慧交通管理系统[J]. 中国交通信息化, 2021(10): 107-109.
	ZHAN Q . Closed-loop digital twin intelligent traffic management system[J]. China ITS Journal, 2021(10): 107-109.
[15]	康宇, 刘雅琼, 赵彤雨 ,等. AI 算法在车联网通信与计算中的应用综述[J]. 电信科学, 2023,39(1): 1-19.
	KANG Y , LIU Y Q , ZHAO T Y ,et al. A survey on AI algorithms applied in communication and computation in Internet of vehicles[J]. Telecommunications Science, 2023,39(1): 1-19.
[16]	ROZEMBERCZKI B , SCHERER P , HE Y X ,et al. PyTorch geometric temporal:spatiotemporal signal processing with neural machine learning models[C]// Proceedings of the 30th ACM International Conference on Information ＆ Knowledge Management. New York:ACM Press, 2021: 4564-4573.
[17]	NAHUM-SHANI I , QIAN M , ALMIRALL D ,et al. Q-learning:a data analysis method for constructing adaptive interventions[J]. Psychological Methods, 2012,17(4): 478-494.
[18]	LOWE R , WU Y , TAMAR A ,et al. Multi-agent actor-critic for mixed cooperative-competitive environments[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:ACM Press, 2017: 6382-6393.
[19]	MNIH V , KAVUKCUOGLU K , SILVER D ,et al. Human-level control through deep reinforcement learning[J]. Nature, 2015,518(7540): 529-533.
[20]	唐慕尧, 周大可, 李涛 . 结合状态预测的深度强化学习交通信号控制[J]. 计算机应用研究, 2022: 1-6.doi:10.19734/j.issn.1001-3695.2021.12.0704.
	TANG M Y , ZHOU D K , LI T . Deep reinforcement learning traffic signal control combined with state prediction[J]. Application Research of Computers, 2022: 1-6.doi:10.19734/j.issn.1001-3695.2021.12.0704.
[21]	PENG Z , LI Q , HUI K M ,et al. Learning to simulate self- driven particles system with coordinated policy optimization[J]. Advances in Neural Information Processing Systems, 2021(34): 10784-10797.
[22]	LOPEZ P A , BEHRISCH M , BIEKER-WALZ L ,et al. Microscopic traffic simulation using SUMO[C]// Proceedings of 2018 21st International Conference on Intelligent Transportation Systems (ITSC). Piscataway:IEEE Press, 2018: 2575-2582.

参数	取值
加速度/(m·s^-2)	2.6
减速度/(m·s^-2)	4.5
车辆长度/m	5.0
最大速度/(km·h^-1)	200
跟车模型	Krauss

基于数字孪生的城市交通流智能预测与导引策略

Digital twin based intelligent urban traffic forecasting and guidance strategy

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 22

相关文章 12

Metrics

推荐阅读 0

[1]	李姗姗, 许建宏, 李涛, 赵永建, 刘志飞. 运营商数字孪生网络能力成熟度模型研究[J]. 电信科学, 2023, 39(6): 149-158.
[2]	胡珈玮, 刘晓谦, 唐昕柯, 董宇涵. 基于DQN的UUV辅助水下无线光通信轨迹规划系统[J]. 电信科学, 2023, 39(5): 42-47.
[3]	刘思杨, 张云飞. 从智能网联1.0到智能网联2.0：面向双智的实时数字孪生城市构建[J]. 电信科学, 2023, 39(3): 32-44.
[4]	康宇, 刘雅琼, 赵彤雨, 寿国础. AI算法在车联网通信与计算中的应用综述[J]. 电信科学, 2023, 39(1): 1-19.
[5]	石珵, 刘朋矩, 杜治钢, 张孙烜, 周振宇, 白晖峰, 何国庆, 孙文文, 马跃. 数字孪生辅助的智能楼宇多模态通信资源管理方法[J]. 电信科学, 2023, 39(1): 60-71.
[6]	邓丹昊, 王朝炜, 江帆, 王卫东. 无人机辅助无蜂窝大规模MIMO中的空地协同调度[J]. 电信科学, 2022, 38(8): 37-44.
[7]	王达, 孙滔, 孙晓文, 郭建超, 孙杰, 陈果, 杨爱东, 欧阳晔. 数字孪生在网络全生命周期管理中的研究[J]. 电信科学, 2022, 38(4): 138-145.
[8]	熊小明, 赵静. 电信运营商云网规划数字化研究和实现[J]. 电信科学, 2022, 38(11): 163-168.
[9]	伍仲丽, 曹园园, 黄文睿, 戴彬, 莫益军. 面向确定性网络的按需智能路由技术[J]. 电信科学, 2021, 37(11): 11-16.
[10]	朱明英, 华竹轩, 史萌. 基于数字化转型的电信综合网格管理的研究和实践[J]. 电信科学, 2021, 37(11): 128-134.
[11]	桂飞,程阳,李丹,洪思虹. 互联网智能路由架构及算法[J]. 电信科学, 2020, 36(10): 12-20.
[12]	刘彬,张云勇. 基于数字孪生模型的工业互联网应用[J]. 电信科学, 2019, 35(5): 120-128.