-
摘要: 为研究诱导模型的诱导效果, 用元胞自动机模型模拟车辆在路网中的行为, 仿真了不同诱导信息在不同交通量、不同受诱导率情况下对交通流的影响, 提出基于Agent的交通诱导模型, 模型采用Q-学习算法优化诱导信息, 可根据路网中交通流情况发布建议性诱导信息, 调节交通流分布。仿真结果表明: 影响诱导效果的主要因素为受诱导率和诱导信息, 基于Agent的交通诱导模型能有效均衡路网交通流, 且随着交通流的增加, 优势逐渐明显。在轻交通量情况下, 该模型较出行者自由选择路径模型略优; 但在重交通量情况下, 发布建议性的诱导信息比描述性诱导信息能减少12%平均行程时间。Abstract: To study the effect of traffic guidance model, cellular automata(CA)model was applied to simulate vehicles' behaviors in traffic network, and the impacts of different guidance informations on traffic flow were studied in different traffic volumes and different accepting guidance ratios.A traffic guidance model based on agent technology was built.In which Q-learning algorithm was used to optimize traffic guidance information, propositional information could be provided according to real time network traffic, traffic flow distribution was adjusted.Simulation result shows that the factors that impact guidance effect in network are accepting guidance ratio and guidance information, traffic guidance model based on agent can effectively balance network traffic flow, which is better to heavy traffic flow.In light traffic flow, the model has a little advantage compared with normal model, but in heavy traffic flow, propositional guidance information can decrease 12% average travel time compared with descriptive guidance information.
-
Key words:
- traffic guidance /
- agent /
- microscopic traffic simulation /
- cellular automata /
- Q-learning algorithm
-
表 1 诱导效果比较
Table 1. Comparison of guidance effects
受诱导率 0.3 0.5 0.7 1.0 诱导效果 行程时间 车辆数 行程时间 车辆数 行程时间 车辆数 行程时间 车辆数 算例1 32.13 13.69 31.70 11.89 31.43 10.54 30.15 8.56 算例2 30.82 12.39 30.91 11.53 30.61 9.93 29.84 7.55 改进/% 4 9 2 3 2 4 7 11 表 2 不同交通量下受诱导率对诱导结果的影响
Table 2. Guidance effects of different accepting guidance ratios in different traffic volumes
交通流量/(veh·s-1) 车辆平均行程时间/s 改进/% Pacc为0.3 Pacc为0.5 Pacc为0.7 Pacc为1.0 0~0.3 31.94 30.82 30.30 30.06 5.0 0~0.5 39.54 37.16 35.79 34.45 12.8 0~0.7 48.83 45.93 42.40 39.62 18.0 表 3 基于Agent诱导模型的诱导效果
Table 3. Effect of traffic guidance model based on agent
交通流量/(veh·s-1) 车辆平均行程时间/s 算例2条件 算例3条件可变受诱导率 Pacc为0.5 Pacc为1.0 0~0.3 30.82 30.06 30.50 0~0.5 37.16 34.45 35.52 0~0.7 45.93 39.62 40.28 -
[1] 马寿峰, 卜军峰, 张安训. 交通诱导中系统最优与用户最优的博弈协调[J]. 系统工程学报, 2005, 20(1): 30-37. https://www.cnki.com.cn/Article/CJFDTOTAL-XTGC200501006.htmMA Shou-feng, BUJun-feng, ZHANG An-xun. Game-based coordination method between systemoptimumand user equi-librium in route guidance system[J]. Journal of Systems Engineering, 2005, 20(1): 30-37. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XTGC200501006.htm [2] 鲁丛林. 诱导条件下的驾驶员反应行为的博弈模型[J]. 交通运输系统工程与信息, 2005, 5(1): 58-61, 87. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT200501010.htmLU Cong-lin. The models of driver s response behavior with game theory under guide information[J]. Journal of Trans-portation Systems Engineering and Information Technology, 2005, 5(1): 58-61, 87. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT200501010.htm [3] 李振龙, 赵晓华. 基于模糊聚类的快速路VMS信息发布方法[J]. 计算机工程, 2008, 34(8): 210-212. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC200808076.htmLI Zhen-long, ZHAO Xiao-hua. Information issuing method of VMS on expressway based on fuzzy clustering[J]. Computer Engineering, 2008, 34(8): 210-212. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC200808076.htm [4] 马晓凤, 严新平. 基于DNA算法的交通诱导系统[J]. 武汉理工大学学报: 交通科学与工程版, 2008, 32(5): 810-813. doi: 10.3963/j.issn.2095-3844.2008.05.010MA Xiao-feng, YAN Xin-ping. Traffic guidance system based on DNAalgorithm[J]. Journal of Wuhan University of Technology: Transportation Science and Engineering, 2008, 32(5): 810-813. (in Chinese) doi: 10.3963/j.issn.2095-3844.2008.05.010 [5] 谷远利, 李善梅, 邵春福. 基于蚁群算法的交通控制与诱导协同研究[J]. 系统仿真学报, 2008, 20(10): 2754-2756, 2761. https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ200810059.htmGU Yuan-li, LI Shan-mei, SHAO Chun-fu. Study on cooper-ation of traffic control and route guidance based on ant algo-rithm[J]. Journal of System Simulation, 2008, 20(10): 2754-2756, 2761. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ200810059.htm [6] WAHLE J, BAZZAN A L C, KLUGL F, et al. The impact of real-time information in a two-route scenario using agent-based simulation[J]. Transportation Research Part C: Emerging Technologies, 2002, 10(5/6): 399-417. [7] NAGEL K, SCHRECKENBERG M. A cellular automaton model for freeway traffic[J]. Journal de Physique I, 1992, 2(12): 2211-2229. [8] 鲁丛林, 谭跃进. 城市交通系统复杂性模型及仿真分析[J]. 系统工程, 2005, 23(3): 84-87. https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT200503016.htmLUCong-lin, TAN Yue-jin. The simulation and analysis of urban transportation system complexity[J]. Systems Engineering, 2005, 23(3): 84-87. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT200503016.htm