Online Optimization Methods for Dynamic Lane
 Configuration at Highway Toll Plazas

doi:10.16097/j.cnki.1009-6744.2025.05.030

Abstract

Abstract: This study addresses the issue of lane configuration optimization at highway toll plazas by proposing a dynamic lane configuration strategy based on reinforcement learning. A simulation environment for highway toll plazas is constructed based on the traffic behavior of vehicles passing through a toll plaza. The complex problem of lane configuration is transformed into a clear quantitative objective function that considers the operational costs of toll plazas, user delay, and congestion penalties. The lane resource allocation strategy of toll plazas is optimized dynamically through the training of a reinforcement learning network. The model is capable of real-time learning and dynamic adjustment of lane configurations to adapt to the dynamic changes in traffic flow and patterns. Experiments comparing the reinforcement learning optimization method with traditional offline optimization methods show that the proximal policy optimization (PPO) method reduces the average queue length by 12.45% and narrows the fluctuation range of average travel time by 26.94%. The PPO algorithm demonstrates advantages in reducing queue length and decreasing the fluctuation in travel time, especially during peak hours. The dynamic lane configuration strategy exhibits higher adaptability and flexibility, enhancing the operational efficiency of toll plazas.

Key words: highway transportation, dynamic lane configuration optimization, reinforcement learning, highway toll plaza; proximal policy optimization (PPO) algorithm

摘要： 针对高速公路收费站车道配置优化问题，本文提出一种基于强化学习的动态车道配置策略。根据车辆通过收费站的交通行为构建高速公路收费站仿真环境，将复杂的车道配置问题转化为考虑收费站运营成本、用户延误和拥堵惩罚的明确量化指标的目标函数，借助强化学习网络训练，动态优化收费站车道资源配置策略。模型能够实时学习并动态调整车道配置，以应对交通流量和模式的动态变化。实验对比了强化学习优化方法与传统离线优化方法，结果表明，PPO(Proximal Policy Optimization)方法在全程平均排队数上降低了12.45%，在平均通过时间的波动范围上缩小了26.94%，PPO算法在减少排队长度和降低通行时间波动方面具有优势，特别是在高峰时段动态车道配置策略展现出更高的适应性和灵活性，提升了收费站的运营效率。

关键词: 公路运输, 车道配置动态优化, 强化学习, 高速公路收费站, PPO算法

CLC Number:

U412.366.1

MA Feihu, CHEN Xiaoyan, SUN Cuiyu, TIAN Xingtong. Online Optimization Methods for Dynamic Lane Configuration at Highway Toll Plazas[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 333-342.

马飞虎, 陈晓燕, 孙翠羽, 田星彤. 高速公路收费站动态车道配置的在线优化方法[J]. 交通运输系统工程与信息, 2025, 25(5): 333-342.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/10.16097/j.cnki.1009-6744.2025.05.030

http://www.tseit.org.cn/EN/Y2025/V25/I5/333

References

[1] 武景顺,黄艳均,武同乐,等.基于VISSIM仿真的高速公路收费站缓堵措施研究:以郑州市东三环南站为例[J]. 综合运输, 2023, 45(11): 187-192. [WU J S, HUANG Y J, WU T L, et al. Congestion mitigation measures of expressway toll station based on VISSM simulation: A case study on the east third ring south station of Zhengzhou[J]. China Transportation Review, 2023, 45(11): 187-192.]

[2] 林培群,梁韫琦.高速公路收费站车道类型设置问题建模与求解[J].交通运输系统工程与信息, 2020, 20(1): 152-159. [LIN P Q, LIANG Y Q. Modeling and solving for lane type setting problem in highway toll station[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 152-159.]

[3] 陈萱怡,郑淑妮.高速公路收费站车道实时配置方案研究[J]. 综合运输, 2023, 45(10): 43-48. [CHEN X Y, ZHENG S N. Real-time lane configuration scheme of expressway toll station[J]. China Transportation Review, 2023, 45(10): 43-48.]

[4] 钱超,李思言,王彦锋.高速公路收费广场车道合理化配置研究[J].交通运输系统工程与信息, 2021, 21(2): 231-237. [QIAN C, LI S Y, WANG Y F. Rationalized lanes configuration for expressway toll plaza[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(2): 231-237.]

[5] 史博,宋锋,李轶群,等.基于交通流预测的高速公路收费站车道开闭配置[J].科学技术与工程, 2023, 23(30): 13157-13164. [SHI B, SONG F, LI Y Q, et al. Lane opening and closing configuration of expressway toll station based on traffic flow prediction[J]. Science Technology and Engineering, 2023, 23(30): 13157-13164.]

[6] 杨涛,王鹏,朱季萍,等.多元收费方式下的高速公路收费站车道数优化研究[J].交通运输系统工程与信息, 2019, 19(5): 212-218. [YANG T, WANG P, ZHU J P, et al. Optimization of lane number of highway toll station based on multiple payments[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(5): 212-218.]

[7] 姬杨蓓蓓,周金凤.基于成本分析的高速公路收费站车道配置研究[J].重庆交通大学学报(自然科学版), 2018, 37(1): 85-91. [JI Y B B, ZHOU J F. Lane allocation of highway toll gate based on cost analysis[J]. Journal of Chongqing Jiaotong University (Natural Science), 2018, 37(1): 85-91.]

[8] 乔建刚,李恩玉,刘怡美,等.智慧高速公路收费站潮汐车道的开放数量研究[J].河北科技大学学报, 2023, 44(1): 83-92. [QIAO J G, LI E Y, LI U Y M, et al. Study on the number of tidal lanes open at smart highway toll stations[J]. Journal of Hebei University of Science and Technology, 2023, 44(1): 83-92.]

[9] 中华人民共和国交通部公路联网收费技术要求附录八: 收费土建附属设施(JTG6310-2022)[S].北京:中华人民共和国交通运输部, 2022. [Ministry of Transport of the People's Republic of China. Technical requirements for highway network toll collection: Appendix VIII -Toll civil engineering ancillary facilities (JTG 6310-2022)[S]. Beijing: Ministry of Transport of the People's Republic of China, 2022.]

[10] 罗杰.高速公路收费站ETC通行特性与车道配置优化研究[D]. 昆明: 昆明理工大学, 2020. [LUO J. Research on ETC traffic characteristics and lane configuration optimization of expressway toll station[D]. Kunming: Kunming University of Science and Technology, 2020.]

[11] 姚成北.基于ETC门架数据的山区高速通行能力研究[D].重庆:重庆交通大学, 2024. [YAO C B. Research on expressway capacity in mountain areas based on ETC gantry data[D]. Chongqing: Chongqing Jiaotong University, 2024.]

[12] NEERAJ R R, NITHIN R P, NIRANJHAN P, et al. Modelling and simulation of discrete manufacturing industry[J]. Materials Today: Proceedings, 2018, 5(11): 24971-24983.

[1]	WANG Jiangfeng, SONG Zhifan, LI Yunfei, QI Chongkai, YAN Xuedong, LI Qingshan. Optimization Algorithm for Ride-hailing Dispatch Under Concentrated Supply and Sparse Demand [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 280-290.
[2]	JIANG Zhijuan, CHEN Meiling, WEI Xintian, HE Jingwen. Assessment of Pollution and Carbon Reduction Potential of Medium-and Heavy-Duty Battery Electric Trucks [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 353-364.
[3]	DAI Liang, DU Pengfei, HUANG Zibin, YANG Pengbo. Hierarchical Collaborative Control of Urban Traffic Signals Based on Deep Reinforcement Learning [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 63-72.
[4]	WANG Xiang, REN Hao, TAN Guozhen, LI Jianping, WANG Jue, WANG Yanli. Autonomous Driving Decision-making Method Based on Cooperative Reinforcement Learning of Large Language Model [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 137-146.
[5]	ZHU Qinyue, LI Jiyuan, LI Hongyi, QIAN Shuyang, ZHAO Yahui. Real-time Robust Optimization of Target Speed Profiles for Urban Rail Trains Considering Load Uncertainty [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 254-264.
[6]	CHEN Bangju, LUO Yikai, CHEN Leilei, WU Hanting, XIANG Changle. A Deep Learning Approach for Enhancement of Hazardous Goods Waybill's Feature [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 306-316.
[7]	XU Jin, LUO Song, CHEN Libiao, LI Tao, WANG Tao. Operating Characteristics of Vehicles Under Hard Shoulders Opening Conditions on Expressways [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(3): 372-382.
[8]	NAN Sirui, YU Qian, LI Tiezhu, SHANG Zandi, CHEN Haibo. Energy-saving Driving Optimization for Connected Electric Buses Considering Station Arrival Strategies [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 82-94.
[9]	DAI Liang, HUANG Zibin, ZHANG Zhonghao, LI Chenfu. Regional Traffic Signal Control Methods Considering Lane Remaining Capacity [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 108-118.
[10]	LIN Junting, LI Maolin, QIU Xiaohui. AJoint Optimization Method of Train Speed Curves and Dynamic Scheduling Under Delay Scenarios [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 173-187.
[11]	DUPeng. Tasks and Measures of Carbon Emission Reduction for China's Traffic and Transportation Industry in the New Period [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 1-4.
[12]	LI Zhe, GOU Yangyang, LI Zhenyao, LI Ao, CEN Wei, GAO Jianping. Dynamic Spatiotemporal Priority Control of Connected Vehicles Public Transport System [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(5): 56-64.
[13]	LIU Dong, ZHANG Dapeng, WAN Yun, XIAO Feng. Single-line Bus Operations Dynamic Holding Control Strategy Based on Deep Reinforcement Learning [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(5): 173-184.
[14]	WEIShuqiao, NI Ying, SUN Jian, QIU Hongtong. Generative Adversarial Imitation Learning Based Bicycle Behaviors Simulation on Road Segments [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 105-115.
[15]	LI Lei, QIAN Sida, XU Liqing, JIAO Wenling, ZHANG Xin, ZHANG Chenghu. Emission Analysis of Hydrogen Fuel Cell Heavy-duty Vehicles Based on Life Cycle Assessment [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 292-299.

Online Optimization Methods for Dynamic Lane Configuration at Highway Toll Plazas

高速公路收费站动态车道配置的在线优化方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics