|Table of Contents|

Variable speed limit control for expressway accident vicinity area in intelligent connected environment(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2025年03期
Page:
152-162
Research Field:
交通工程
Publishing date:

Info

Title:
Variable speed limit control for expressway accident vicinity area in intelligent connected environment
Author(s):
WANG Yue-jiao1;  LU Xiao-juan2;  ZHENG Shi-yu3;  ZHAO Wen-ding4;  LI Wei-jia5
(1. Key Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University,Shanghai 201804, China; 2. School of Traffic and Transportation, Lanzhou Jiaotong University,Lanzhou 730070, Gansu, China; 3. School of Transportation Engineering, Chang'an University, Xi'an 710064, Shaanxi, China; 4. CCCC Second Highway Consultants Co., Ltd., Wuhan 430056, Hubei, China; 5. School of Architecture,Chang'an University, Xi'an 710064, Shaanxi, China)
Keywords:
traffic engineering;  variable speed limit control;  deep reinforcement learning;  expressway accident area;  intelligent connected transportation
PACS:
U491.54
DOI:
10.19721/j.cnki.1671-8879.2025.03.013
Abstract:
To improve the control effect of variable speed limit(VSL)for expressway accident vicinity area in mixed traffic environment with connected and autonomous vehicle(CAV)and human-driven vehicle(HDV), based on the advantages of the twin delayed deep deterministic policy gradient(TD3)algorithm in automatically adapting to complex environments and the controllability of CAV, the intelligent connected environment was applied to monitor the traffic flow state of the controlled road section in real time, and the action space, state space and reward function of the algorithm were determined. The TD3-variable speed limit(TD3-VSL )control strategy based on the dynamic delay strategy to update the TD3 algorithm was proposed. Taking a two-way four-lane section of G75 Lanzhou-Haikou Expressway as the research object, a traffic flow simulation environment conformed to actual road characteristics was constructed through the SUMO simulation platform. The simulation parameters were calibrated with reference to the traffic data collected in the field. Three comparative experimental schemes such as no dynamic speed limit control, feedback speed limit control and TD3-VSL control were designed to verify the effectiveness of different control strategies. The downstream traffic volumes and vehicle speed standard deviations under different CAV penetration rates were compared and analyzed. The research results show that compared with the no dynamic speed limit control strategy and feedback speed limit control, the TD3-VSL control strategy can more effectively improve the traffic efficiency after the congestion occurs. The mean speed standard deviation reduces by 58.4% and 75.8%, respectively, and the published speed limit standard deviation reduces by 28.3%. With the increase in the CAV penetration rate, the control effect of TD3-VSL further improves, and the traffic congestion alleviates. When the CAV penetration rate is 40%, the vehicle speed standard deviation is 44.11% lower than that of the pure human driving scene. When the CAV penetration rate increases to 80%, the decrease is further up to 54.46%. The research results provide a theoretical basis for expressway safety management in intelligent connected environment, and have reference value for reducing the incidence of traffic accidents and optimizing the operation efficiency of road network.2 tabs, 10 figs, 31 refs.

References:

[1] 宿永辉,欧阳涛,潘新福,等.面向高速公路连续瓶颈的协同可变限速控制[J].交通运输工程与信息学报,2024,22(3):166-180.
SU Yong-hui, OUYANG Tao, PAN Xin-fu, et al. A collaborative variable speed-limit control for continuous bottlenecks on freeways[J]. Journal of Transportation Engineering and Information, 2024, 22(3): 166-180.
[2]周昭明,黄中祥,袁剑波,等.基于无人驾驶车辆的不同车道模式交通流优化[J].长安大学学报(自然科学版),2021,41(1):103-115.
ZHOU Zhao-ming, HUANG Zhong-xiang, YUAN Jian-bo, et al. Traffic flow optimization of different lane modes based on autonomous vehicles[J]. Journal of Chang'an University(Natural Science Edition), 2021, 41(1): 103-115.
[3]李 春,吴志周,曾 广,等.合流区智能网联汽车协同控制方法综述[J].计算机工程与应用,2024,60(12):1-17.
LI Chun, WU Zhi-zhou, ZENG Guang, et al. Review of connected autonomous vehicle cooperative control at on-ramp merging areas[J]. Computer Engineering and Applications, 2024, 60(12): 1-17.
[4]何庆龄,刘 静,李 珊,等.基于SO-BiLSTM的高速公路交通事故持续时间预测[J].重庆交通大学学报(自然科学版),2024,43(10):97-105.
HE Qing-ling, LIU Jing, LI Shan, et al. Highway traffic accident duration prediction based on SO-BiLSTM[J]. Journal of Chongqing Jiaotong University(Natural Science), 2024, 43(10): 97-105.
[5]徐建闽,廖冬梅,马莹莹.高速公路事故瓶颈区域可变限速控制方法[J].重庆交通大学学报(自然科学版),2022,41(11):25-33.
XU Jian-min, LIAO Dong-mei, MA Ying-ying. Variable speed limit control method for accident bottleneck region on freeway[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(11): 25-33.
[6]DU S M, RAZAVI S. Variable speed limit for freeway work zone with capacity drop using discrete-time sliding mode control[J]. Journal of Computing in Civil Engineering, 2019, 33(2): 04019001.
[7]王 静,雷利利,熊晓夏,等.考虑通信延迟的智能车队纵向控制[J].交通运输工程与信息学报,2024,22(4):37-51.
WANG Jing, LEI Li-li, XIONG Xiao-xia, et al. Longitudinal control of intelligent fleet considering communication delay[J]. Journal of Transportation Engineering and Information, 2024, 22(4): 37-51.
[8]SELIMAN S M S, SADEK A W, HE Q. Optimal variable,lane group-based speed limits at freeway lane drops: a multiobjective approach[J]. Journal of Transportation Engineering, Part A: Systems, 2020, 146(8): 04020074.
[9]HAN Y, WANG M, HE Z A, et al. A linear Lagrangian model predictive controller of macro- and micro-variable speed limits to eliminate freeway jam waves[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103121.
[10]ZHENG S, LI M, KE Z M, et al. Coordinated variable speed limit control for consecutive bottlenecks on freeways using multiagent reinforcement learning[J]. Journal of Advanced Transportation, 2023, 2023(1): 4419907.
[11]ROY A, HOSSAIN M, MUROMACHI Y. A deep reinforcement learning-based intelligent intervention framework for real-time proactive road safety management[J]. Accident Analysis and Prevention, 2022, 165: 106512.
[12]刘 东,张大鹏,万 芸,等.基于深度强化学习的单线路公交动态驻站控制策略研究[J].交通运输系统工程与信息,2024,24(5):173-184.
LIU Dong, ZHANG Da-peng, WAN Yun, et al. 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.
[13]WU Y K, TAN H C, QIN L Q, et al. Differential variable speed limits control for freeway recurrent bottlenecks via deep actor-critic algorithm[J]. Transportation Research Part C: Emerging Technologies, 2020, 117: 102649.
[14]余荣杰,徐 灵,章锐辞.基于多智能体深度强化学习的高速公路可变限速协同控制方法[J].同济大学学报(自然科学版),2024,52(7):1089-1098.
YU Rong-jie, XU Ling, ZHANG Rui-ci. Coordinated variable speed limit control for freeway based on multi-agent deep reinforcement learning[J]. Journal of Tongji University(Natural Science), 2024, 52(7): 1089-1098.
[15]JIN J L, HUANG H L, LI Y, et al. Variable speed limit control strategy for freeway tunnels based on a multi-objective deep reinforcement learning framework with safety perception[J]. Expert Systems with Applications, 2025, 267: 126277.
[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 Wei-an. 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]YU M, FAN W D. Optimal variable speed limit control in connected autonomous vehicle environment for relieving freeway congestion[J]. Journal of Transportation Engineering, Part A: Systems, 2019, 145(4): 04019007.
[18]过秀成,肖 哲,张一鸣,等.考虑智能网联车辆影响的八车道高速公路施工区可变限速控制方法[J].东南大学学报(自然科学版),2024,54(2):353-359.
GUO Xiu-cheng, XIAO Zhe, ZHANG Yi-ming, et al. Variable speed limit control method in work zone area of eight-lane highway considering effects of connected automated vehicles[J]. Journal of Southeast University(Natural Science Edition), 2024, 54(2): 353-359.
[19]ZHAO F Y, LI D Y, WANG Z X, et al. Autonomous localized path planning algorithm for UAVs based on TD3 strategy[J]. Scientific Reports, 2024, 14: 763.
[20]SHU M, SHUAI L, GONG X Y, et al. Episodic memory-double actor-critic twin delayed deep deterministic policy gradient[J]. Neural Networks, 2025, 187: 107286.
[21]TUNC I, SOYLEMEZ M T. Fuzzy logic and deep Q learning based control for traffic lights[J]. Alexandria Engineering Journal, 2023, 67: 343-359.
[22]ZENG J W, QIAN Y S, LYU Z W, et al. Expressway traffic flow under the combined bottleneck of accident and on-ramp in framework of Kerner's three-phase traffic theory[J]. Physica A: Statistical Mechanics and its Applications, 2021, 574: 125918.
[23]曹宁博,陈家辉,赵利英.智能网联车和人驾车辆混合交通流排队长度估计模型[J].浙江大学学报(工学版),2024,58(9):1935-1944.
CAO Ning-bo, CHEN Jia-hui, ZHAO Li-ying. Queue length estimation model for mixed traffic flow of intelligent connected vehicles and human-driven vehicles[J]. Journal of Zhejiang University(Engineering Science), 2024, 58(9): 1935-1944.
[24]程国柱,王文志,汪国鹏,等.设置专用车道场景下快速路分流区智能网联车辆决策方法[J/OL].吉林大学学报(工学版),(2025-03-11)[2025-04-22].https://doi.org/10.13229/j.cnki.jdxbgxb.20241269.
CHENG Guo-zhu, WANG Wen-zhi, WANG Guo-peng, et al. Connected and automated vehicles decision-making method for expressway diversion areas with dedicated lanes[J/OL]. Journal of Jilin University(Engineering and Technology Edition),(2025-03-11)[2025-04-22]. https://doi.org/10.13229/j.cnki.jdxbgxb.20241269.
[25]邢 璐,曹一君,金孔宁,等.基于客货智能网联车辆的高速公路瓶颈区两阶段动态限速控制方法[J/OL].中国公路学报,(2025-04-01)[2025-04-11].http://kns.cnki.net/kcms/detail/61.1313.U.20250331.1727.004.html.
XING Lu, CAO Yi-jun, JIN Kong-ning, et al. A two-stage dynamic speed control method for freeway bottlenecks based on connected and automated cars and trucks[J/OL]. China Journal of Highway and Transport,(2025-04-01)[2025-04-11]. http://kns.cnki.net/kcms/detail/61.1313.U.20250331.1727.004.html.
[26]ZHANG L, DING H, FENG Z, et al. Variable speed limit control strategy considering traffic flow lane assignment in mixed-vehicle driving environment[J]. Physica A: Statistical Mechanics and Its Applications, 2024, 656: 130216.
[27]TREIBER M, KESTING A. The intelligent driver model with stochasticity-new insights into traffic flow oscillations[J]. Transportation Research Part B: Methodological, 2018, 117: 613-623.
[28]谷梦路,葛振振,王 畅,等.智能网联车辆加速车道类人化汇入控制研究[J].中国公路学报,2024,37(3):134-146.
GU Meng-lu, GE Zhen-zhen, WANG Chang, et al. Human-like merging control of intelligent connected vehicles on the acceleration lane[J]. China Journal of Highway and Transport, 2024, 37(3): 134-146.
[29]何庆龄,裴玉龙,董春彤,等.基于混合策略改进ASO-LSSVM的风险驾驶行为分类识别[J].华南理工大学学报(自然科学版),2024,52(9):131-141.
HE Qing-ling, PEI Yu-long, DONG Chun-tong, et al. Classification and identification of risky driving behavior based on hybrid strategy improved ASO-LSSVM[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(9): 131-141.
[30]CANDELIERI A, PONTI A, ARCHETTI F. Fair and green hyperparameter optimization via multi-objective and multiple information source Bayesian optimization[J]. Machine Learning, 2024, 113(5): 2701-2731.
[31]龚思远,郑国辉,曾 露,等.迈向智能网联的可变限速控制研究综述:技术演进、工程应用和未来展望[J].交通运输工程与信息学报,2025,23(1):1-35.
GONG Si-yuan, ZHENG Guo-hui, ZENG Lu, et al. A review of studies on variable speed limit control toward the era of connected and autonomous transportation: Technological evolution,engineering applications,and future prospects[J]. Journal of Transportation Engineering and Information, 2025, 23(1): 1-35.

Memo

Memo:
-
Last Update: 2025-05-30