|
|
基于Swarm和机器学习的城市道路交通系统多主体仿真研究
|
Abstract:
城市道路交通系统仿真是分析和优化现有城市交通系统的重要方法之一。本文设计了基于Swarm和DQN机器学习算法的多主体仿真模型。首先，基于复杂适应系统理论，建立了多主体仿真模型。对于系统中主体的个体决策行为采用机器学习中的DQN算法来模拟，并基于Swarm软件包实现了所设计的仿真模型。最后，使用滴滴出行盖亚数据开放计划中成都市二环线上的数据对所建立的模型进行了仿真和分析，结果表明了方法的有效性。
Urban road traffic system simulation is one of the important methods to analyze and optimize the existing urban traffic system. In this paper, a multi-agent simulation model based on Swarm and DQN machine learning algorithm is designed. Firstly, based on complex adaptive system theory, a multi-agent simulation model is established. Then the DQN machine learning algorithm is used to simulate the individual decision-making behavior of the agent in the system. The simulation model is implemented based on Swarm software package. Finally, the model is simulated and analyzed by using the data from the second ring line of Chengdu City in the Gaia Data Open Plan. The result illustrates the effectiveness of this method.
| [1] | 毛保华, 杨肇夏, 陈海波. 道路交通仿真技术与系统研究[J]. 北方交通大学学报, 2002(5): 37-46. |
| [2] | 邹智军. 新一代交通仿真技术综述[J]. 系统仿真学报, 2010, 22(9): 2037-2042. |
| [3] | 石敏, 孙科, 毛天露, 郑玲. 面向智能交通系统的仿真路网快速建模方法[J]. 图学学报, 2019, 40(3): 489-496. |
| [4] | 黄敏, 饶明雷, 李敏. 面向仿真的车道级基础路网模型及其应用[J]. 系统仿真学报, 2014, 26(3): 657-661. |
| [5] | 秦天保, 刘兰辉, 沙梅. 集装箱码头堆场道路交叉口车流仿真研究[J]. 系统仿真学报, 2014, 26(2): 430-434. |
| [6] | Samaras, C., Tsokolis, D., Toffolo, S., Magra, G., Ntziachristos, L. and Samaras, Z. (2019) Enhancing Average Speed Emission Models to Account for Con-gestion Impacts in Traffic Network Link-Based Simulations. Transportation Research Part D: Transport and Envi-ronment, 75, 197-210. https://doi.org/10.1016/j.trd.2019.08.029 |
| [7] | Feliciani, C., Gorrini, A., Crociani, L., Vizzari, G., Nishinari, K. and Bandini, S. (2019) Calibration and Validation of a Simulation Model for Predicting Pedestrian Fatalities at Unsignalized Crosswalks by Means of Statistical Traffic Data. Journal of Traffic and Transportation Engineering (English Edition). https://doi.org/10.1016/j.jtte.2019.01.004 |
| [8] | Mubasher, M.M., Jaffry, S.W., Yousaf, M.M., Bajwa, I.S., Sarwar, S. and Aslam, L. (2019) A Smart Integrated Environment for Vehicular Traffic Simulation. International Journal of Communication Systems, 32, e4029. https://doi.org/10.1002/dac.4029 |
| [9] | Macal, C. and North, M. (2010) Tutorial on Agent-Based Modelling and Simulation. Journal of Simulation, 4, 151-162. https://doi.org/10.1057/jos.2010.3 |
| [10] | Itami, R., Raulings, R., MacLaren, G., Hirst, K., Gimblett, R. and Zanon, D. (2003) Simulating the Complex Interactions between Human Movement and the Outdoor Recreation Environment. Journal for Nature Conservation, 11, 278-286. https://doi.org/10.1078/1617-1381-00059 |
| [11] | Lv, R.J. and Zhang, J.S. (2012) Multi-Agent Simulation in Inte-grated Passenger Transportation System under Uncertain Environment. Journal of Theoretical and Applied Information Technology, 49, 651-655. |
| [12] | 唐俊. 基于多主体模型的兰州市城市空间演化过程及动态模拟[D]: [硕士学位论文]. 西安: 西北大学, 2016. |
