Multi-agent modeling of traffic organization in urban agglomerations

: 10-22
Received: March 04, 2024
Accepted: April 20, 2024
National University of Life and Environmental Sciences of Ukraine
National University of Life and Environmental Sciences of Ukraine

The authors consider the features of multi-agent modeling for traffic optimization in the central areas of cities. While evaluating the unique challenges associated with the high concentration of vehicles, pedestrians and historical buildings, the potential of multi-agent systems to effectively solve the problem of congestion, safety and quality of life in urban areas is investigated. The potential of multi-agent modeling in the context of traffic management in the central areas of the city allows us to identify the key challenges and opportunities. Many scientists address the main aspects of such modeling and use them in the transport and road sectors. A review of current research and development has shown that multi-agent models aim to simulate and optimize the supervision and control of transportation in various traffic scenarios. Modeling traffic organization in the central areas of cities is one of the main elements of urban development planning and management. Due to the growing population of cities and the increasing number of vehicles, the problems of congestion, air pollution, and inefficient use of infrastructure are becoming increasingly relevant. Therefore, it can be noted that multi-agent traffic modeling opens up new prospects for developing effective traffic management strategies, providing a flexible and adaptive solution to these problems. The research analyzes the existing approaches, identifies the system`s key components, and develops a model that demonstrates the interaction between agents and the environment based on a mathematical description. A practical simulation of the model, carried out using the AnyLogic software on the example of Lesia Ukrainka Boulevard in Kyiv, confirms the effectiveness of the multi-agent approach. The results of the study indicate the possibility of applying the developed model to improve intelligent information systems for traffic flow management, which opens up new prospects for improving traffic in the central areas of cities.

1. Titarmare, A. S., Khanapurkar, M. M., & Chandankhede, P. H. (2020). Analysis of traffic flow at intersection to avoid accidents using Nagel-Schreckenlerg model. In 2020 Fourth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (pp. 478-484). IEEE. doi: 10.1109/I-SMAC49090.2020.9243306 (in English).
2. Dukić, A., Bjelošević, R., Stojčić, M., & Banjanin, M. K. (2023). Network Model of Multiagent Communication of Traffic Inspection for Supervision and Control of Passenger Transportation in Road and City Traffic. In 2023 46th MIPRO ICT and Electronics Convention (MIPRO) (pp. 1167-1172). IEEE. doi: 10.23919/MIPRO57284.2023.10159771 (in English).
3. Wang, J., Lv, W., Jiang, Y., Qin, S., & Li, J. (2021). A multi-agent based cellular automata model for intersection traffic control simulation. Physica A: Statistical Mechanics and its Applications, 584, 126356. doi: 10.1016/J.PHYSA.2021.126356 (in English).
4. Wang, S., & Wang, S. (2023). A Novel Multi-Agent Deep RL Approach for Traffic Signal Control. Computer Science. Retrieved from: (in English).
5. Liu, D., & Li, L. (2023). A traffic light control method based on multi-agent deep reinforcement learning algorithm. Scientific Reports, 13(1), 9396. doi: 10.1038/s41598-023-36606-2 (in English).
6. Learning Multi-intersection Traffic Signal Control via Coevolutionary Multi-Agent Reinforcement Learning. Retrieved from: (in English).
7. Zhuang, H., Lei, C., Chen, Y., & Tan, X. (2023). Cooperative Decision-Making for Mixed Traffic at an Unsignalized Intersection Based on Multi-Agent Reinforcement Learning. Applied Sciences, 13(8), 5018. doi: 10.3390/app13085018 (in English).
8. Mushtaq, A., Haq, I. U., Sarwar, M. A., Khan, A., Khalil, W., & Mughal, M. A. (2023). Multi-agent reinforcement learning for traffic flow management of autonomous vehicles. Sensors, 23(5), 2373. doi: 10.3390/s23052373 (in English).
9. Le, N. T. T. (2023). Multi-agent reinforcement learning for traffic congestion on one-way multi-lane highways. Journal of Information and Telecommunication, 7(3), 255-269. doi: 10.1080/24751839.2023.2182174 (in English).
10. Liu, Q., Li, Z., Li, X., Wu, J., & Yuan, S. (2022, October). Graph convolution-based deep reinforcement learning for multi-agent decision-making in interactive traffic scenarios. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) (pp. 4074-4081). IEEE. doi: 10.1109/ITSC55140.2022.9922001 (in English).
11. Zouari, M., Baklouti, N., Kammoun, M. H., Ayed, M. B., Alimi, A. M., & Sanchez-Medina, J. (2021, July). A multi-agent system for road traffic decision making based on hierarchical interval type-2 fuzzy knowledge representation system. In 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp. 1-6). IEEE. doi: 10.1109/FUZZ45933.2021.9494502 (in English).
12. Bastarianto, F. F., Hancock, T. O., Choudhury, C. F., & Manley, E. (2023). Agent-based models in urban transportation: review, challenges, and opportunities. European Transport Research Review, 15(1), 19. doi: 10.1186/s12544-023-00590-5 (in English).
13. Hamza, A., Rizvi, S. T. H., Safder, M. U., & Asif, H. (2022). A Novel Mathematical Approach to Model Multi-Agent-Based Main Grid and Microgrid Networks for Complete System Analysis. Machines, 10(2), 110. doi: 10.3390/machines10020110 (in English).
14. Mathematical modeling of multi-agent search & task allocation. Retrieved from: (in English).