Collaborative Control for Urban Expressway Mainline and On-Ramp Metering in Connected-Vehicle Environment

doi:10.12141/j.issn.1000-565X.240403

Abstract

Abstract:

With the increasing application of Connected and Autonomous Vehicle (CAV) technologies in active traffic management, Variable Speed Limit (VSL) strategies have become crucial for improving traffic flow efficiency and safety. To address the issues of decreased traffic capacity and abrupt speed variations caused by traffic conflicts in urban expressway merging areas, a cooperative variable speed limit (VSL) control strategy was proposed for the mainline and on-ramp under a connected vehicle environment. Firstly, a mainline traffic flow prediction model based on Motorway Traffic Flow Network Modle (METANET) was adopted, constructing a bi-objective function to minimize the total travel time and distance, using Model Predictive Control (MPC). Then, the variable speed limit control problem was modelled as a Markov decision process, with a composite reward function based on average speed, throughput, and vehicle delay. By introducing Deep Q-network (DQN), the optimal on-ramp speed limits under different traffic flow conditions were calculated and disseminated to CAVs through Vehicle-to-Infrastructure (V2I) communication. Finally, the proposed coordinated control strategy was simulated and tested using the North Third Ring Expressway in Xuzhou, China as a case study. The empirical results based on SUMO microsimulation demonstrate that the proposed strategy, compared to the scenario with speed control only on the mainline, reduces the total travel time of network vehicles by 8.51%, increases the average speed by 14.49%, and reduces traffic density fluctuations by 14.81%. These results demonstrate that the proposed method can effectively improve traffic flow efficiency in merging areas under a connected vehicle environment, reduce speed differences between mainline and ramp vehicles, and shrink the spatiotemporal scope of congestion, thereby enhancing the stability of urban expressway traffic flow.

Key words: intelligent transportation, variable speed limit, Deep Q-network, urban expressway, on-ramp control, motorway traffic flow network modle

CLC Number:

U491.4

WU Haodu, SHI Yang, ZHAO Junteng, SUN Jian. Collaborative Control for Urban Expressway Mainline and On-Ramp Metering in Connected-Vehicle Environment[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(8): 73-86.

Figures/Tables 17

Fig.1

Table 1

Parameter of METANET calibration results"

参数	数值		数值
$τ$ /s	10.8	每车道 $Q m a x$ /（辆 $∙$ h^-1）	1 910
$ν$ /（km² $∙$ h^-1）	26	每车道 $ρ J a m$ /（辆 $∙$ km^-1）	157
$ε$ /（辆 $∙$ km^-1）	40	每车道 $ρ c r$ /（辆 $∙$ km^-1）	22
$v f$ /（km $∙$ h^-1）	85	$T$ /s	60

Table 1

Fig.2

Fig.3

Table 2

DQN model parameter settings"

参数	数值
学习率 $α$	0.001
折扣因子 $γ$	0.95
经验缓冲区容量 $m$	10⁴
目标网络参数替换值 $τ r$	50
最大探索率 $ε m a x$	1
衰减率 $ε d e c a y$	0.995
隐藏层数量 $h$	3
每层神经元数量 $n$	64

Table 2

Fig.4

Fig.5

Table 3

CACC model parameter settings"

系统参数	仿真设置
换道模型	LC2013
速度系数	1
跟驰模型	CACC
$k p$	0.45
$k d$	0.25
$l$ /m	5
$t c$ /s	0.6
$∆ k$ /s	0.1

Table 3

Fig.6

Fig.7

Fig.8

Table 4

Simulation results of parameters under different control strategies"

控制策略	总行程时间/ （辆 $∙$ h）	总行驶距离/ （辆 $∙$ km）	匝道排队长度/m	交通流量/ （辆 $∙$ h^-1）		交通密度/ （辆 $∙$ km^-1）		排放量/ （mg·辆^-1）
控制策略	总行程时间/ （辆 $∙$ h）	总行驶距离/ （辆 $∙$ km）	匝道排队长度/m	均值	标准差	均值	标准差	CO₂	NO _x	HC
无控制	293.98	9 847.70	184	4 041	161.67	130	20	888 788.22	357.10	64.65
F-VSL	283.49/（-3.57%）^1）	10 977.24/（+11.47%）^2）	162/ （+11.96%）^3）	4 495	144.54	120	26	739 990.71/（-16.74%）^4）	295.97	52.64
M-VSL	278.29/（-5.34%）^1）	11 374.88/（+15.51%）^2）	138/ （+25.00%）^3）	4 654	158.36	115	27	689 397.96/（-22.43%）^4）	275.39	48.80
C-DRL-VSL	254.61/（-13.39%）^1）	11 834.16/（+20.17%）^2）	86/ （+53.26%）^3）	4 868	135.50	103	23	656 371.47/（-26.15%）^4）	261.64	46.10

Table 4

Fig.9

Fig.10

Fig.11

Table 5

Fig.12

References 30

[1]	ZHAO J， MA W， XU H ．Increasing the capacity of the intersection downstream of the freeway off-ramp using presignals［J］．Computer-Aided Civil and Infrastructure Engineering，2017，32（8）：674-690.
[2]	KHONDAKER B， KATTAN L ．Variable speed limit：an overview［J］．Transportation Letters，2015，7（5）：264-278.
[3]	余向华．快速路瓶颈通行能力陡降动态建模与交通控制机理解析［D］．杭州：浙江大学，2023.
[4]	PAPAGEORGIOU M， KOSMATOPOULOS E， PAPAMICHAIL I ．Effects of variable speed limits on motorway traffic flow［J］．Transportation Research Record，2008，2047（1）：37-48.
[5]	HEGYI A， DE SCHUTTER B， HELLENDOORN H ．Model predictive control for optimal coordination of ramp metering and variable speed limits［J］．Transportation Research Part C：Emerging Technologies，2005，13（3）：185-209.
[6]	LIU H， ZHANG L， SUN D，et al ．Optimize the se-ttings of variable speed limit system to improve the performance of freeway traffic［J］．IEEE Transactions on Intelligent Transportation Systems，2015，16（6）：3249-3257.
[7]	周浩，胡坚明，张毅，等．快速路可变限速与匝道控制协同优化策略［J］．交通运输系统工程与信息，2017，17（2）：68-75.
	ZHOU Hao， HU Jianming， ZHANG Yi，et al ．A coordinated optimization strategy of variable speed limit and ramp metering for expressway［J］．Journal of Transportation Systems Engineering and Information Technology，2017，17（2）：68-75.
[8]	ARORA K， KATTAN L ．Operational and safety impacts of integrated variable speed limit with dynamic hard shoulder running［J］．Journal of Intelligent Transportation Systems，2023，27（6）：769-798.
[9]	MCCARTT A T， NORTHRUP V S， RETTING R A ．Types and characteristics of ramp-related motor vehicle crashes on urban interstate roadways in Northern Virginia［J］．Journal of Safety Research，2004，35（1）：107-114.
[10]	GUO Y， LI Z， SAYED T ．Analysis of crash rates at freeway diverge areas using Bayesian Tobit modeling framework［J］．Journal of The Transportation Research Board，2019，2673（4）：652-662.
[11]	CHENG M， ZHANG C H， JIN H，et al ．Adaptive coordinated variable speed limit between highway mainline and on-ramp with deep reinforcement learning［J］．Journal of Advanced Transportation，2022（1）： 2435643/1-11.
[12]	WALRAVEN E， SPAAN M T J， BAKKER B ．Traffic flow optimization：a reinforcement learning approach［J］．Engineering Applications of Artificial Intelligence，2016，52：203-212.
[13]	ZHU F， UKKUSURI S V ．Accounting for dynamic speed limit control in a stochastic traffic environment：a reinforcement learning approach［J］．Transportation Research Part C：Emerging Technologies，2014，41：30-47.
[14]	GREGURIĆ M， KUŠIĆ K， VRBANIĆ F，et al ．Variable speed limit control based on deep reinforcement learning：A possible implementation［C］∥Proceedings of the 2020 International Symposium ELMAR．［S.l.］：IEEE， 2020：67-72.
[15]	白如玉，焦朋朋，陈越，等．基于强化学习的车道级可变限速控制策略［J］．交通信息与安全，2024，42（1）：105-114.
	BAI Ruyu， JIAO Pengpeng， CHEN Yue，et al ．Di-fferential variable speed limit control strategy based on reinforcement learning［J］．Journal of Transport Information and Safety，2024，42（1）：105-114.
[16]	韩磊，张轮，郭为安．混合交通流环境下基于改进强化学习的可变限速控制策略［J］．交通运输系统工程与信息，2023，23（3）：110-122.
	HAN Lei， ZHANG Lun， GUO Weian ．Variable speed limit control based on improved dueling double deep Q network under mixed traffic environment［J］．Journal of Transportation Systems Engineering and Information Technology，2023，23（3）：110-122.
[17]	WU J， QU X ．Intersection control with connected and automated vehicles： a review［J］．Journal of Intelligent and Connected Vehicles，2022，5（3）：260-269.
[18]	VRBANIĆ F， TIŠLJARIĆ L， MAJSTOROVIĆ Ž，et al ．Reinforcement learning-based dynamic zone placement variable speed limit control for mixed traffic flows using speed transition matrices for state estimation［J］．Machines，2023，11（4）：479-494.
[19]	WANG X， ZHANG R， GOU Y，et al ．Variable speed limit control method of freeway mainline in intelligent connected environment［J］．Journal of Advanced Transportation，2021（1）：8863487/1-12.
[20]	邵敬波，黄轲，张兆磊，等．高速公路连续瓶颈混合交通流可变限速与换道协同控制方法［J］．交通信息与安全，2023，41（3）：59-68，79.
	SHAO Jingbo， HUANG Ke， ZHANG Zhaolei，et al ．A cooperative control method of variable speed limit and lane change for mixed traffic flow on continuous bottlenecks of freeway［J］．Journal of Transport Information and Safety，2023，41（3）：59-68，79.
[21]	KONTORINAKI M， SPILIOPOULOU A， RONCOLI C，et al ．First-order traffic flow models incorporating capacity drop：overview and real-data validation［J］．Transportation Research Part B：Methodological，2017，106：52-75.
[22]	PAPAGEORGIOU M， PAPAMICHAIL I， SPILIOPOULOU A D，et al ．Real-time merging traffic control with app-lications to toll plaza and work zone management［J］．Transportation Research Part C：Emerging Technologies，2008，16（5）：535-553.
[23]	HADIUZZAMAN M， QIU T Z， LU X Y ．Variable speed limit control design for relieving congestion caused by active bottlenecks［J］．Journal of Transportation Engineering，2013，139（4）：358-370.
[24]	DERVISOGLU G， GOMES G， KWON J，et al ．Automatic calibration of the fundamental diagram and empirical observations on capacity［C］∥Proceedings of the Transportation Research Board 88th Annual Meeting. Washington D C：TRB，2009：31-59.
[25]	GAO H， JIA H， WU R，et al ．Variable speed limit control for mixed traffic flow on highways based on deep-reinforcement learning［J］．Journal of Transportation Engineering，Part A：Systems，2024，150（3）：04023147/1-19.
[26]	AHMIC K， TAHIRBEGOVIC A， TAHIROVIC A，et al ．Simulation framework for platooning based on gazebo and SUMO［C］∥Proceedings of the 2020 IEEE 3rd Connected and Automated Vehicles Symposium （CAVS）. Victoria：IEEE，2020：1-7.
[27]	姚志洪，顾秋凡，徐桃让，等．考虑时延的智能网联汽车混合交通流稳定性分析［J］．控制与决策，2022，37（6）：1505-1512.
	YAO Zhihong， GU Qiufan， XU Taorang，et al ．Stability of mixed traffic flow with intelligent connected vehicles considering time delay［J］．Control and Decision，2022，37（6）：1505-1512.
[28]	JIA D， NGODUY D， VU H L ．A multiclass microscopic model for heterogeneous platoon with vehicle-to-vehicle communication［J］．Transportmetrica B：Transport Dynamics，2019，7（1）：311-335.
[29]	秦严严，王昊，王炜，等．混有协同自适应巡航控制车辆的异质交通流稳定性解析与基本图模型［J］．物理学报，2017，66（9）：094502/1-9.
	QIN Yanyan， WANG Hao， WANG Wei，et al ．Stability analysis and fundamental diagram of heterogeneous traffic flow mixed with cooperative adaptive cruise control vehicles［J］．Acta Physica Sinica，2017，66（9）：094502/1-9.
[30]	孙健，宋茂星，邱果，等．基于电动汽车大数据的多等级充电站选址与服务能力研究［J］．中国公路学报，2024，37（4）：48-60.
	SUN Jian， SONG Maoxing， QIU Guo，et al ．Location and service capability of multilevel charging stations based on electric vehicle big data［J］．China Journal of Highway and Transport，2024，37（4）：48-60.

交通需求场景	控制策略	交通流量/ （辆∙h^-1）	交通流量改善百分比/%	速度标准差/ （km∙h^-1）	速度标准差改善百分比/%	匝道排队长度/m	匝道排队长度改善百分比/%
场景1	无控制	4 102	—	1.49	—	156	—
	F-VSL	4 256	3.75	2.62	-75.84	133	14.74
	M-VSL	4 328	5.51	2.41	-61.74	128	17.95
	C-DRL-VSL	4 459	8.70	1.46	2.01	65	58.33
场景2	无控制	4 041	—	2.03	—	184	—
	F-VSL	4 495	11.23	3.04	-49.75	162	11.96
	M-VSL	4 654	15.17	3.55	-74.88	138	25.00
	C-DRL-VSL	4 868	20.47	1.51	25.62	86	53.26
场景3	无控制	5 040	—	1.28	—	206	—
	F-VSL	5 182	2.82	1.96	-53.13	185	10.19
	M-VSL	5 278	4.72	1.88	-46.88	176	14.56
	C-DRL-VSL	5 396	7.06	1.53	-19.53	134	34.95