Urban Transport Systems Optimization Through Real-Time Data Analytics
Keywords:
Artificial Intelligence, Intelligent Transportation Systems, Traffic Signal Control, Real-Time Data Analytics, LightGBM, Reinforcement Learning, Max-Pressure Control, Microscopic Traffic SimulationAbstract
Urban traffic congestion continues to increase travel time, fuel consumption, and environmental impact in modern cities, and Tbilisi is no exception: traffic intensity at signalized intersections varies sharply depending on time of day, direction, and the workday–weekend cycle. This study proposes an integrated, AI-assisted framework that connects real-time route-level traffic observation, short-term forecasting, and adaptive signal control within a single decision-support pipeline. Traffic data were collected at five-minute intervals for twelve origin–destination route pairs surrounding one critical intersection in Tbilisi using the Google Routes API, with automated acquisition and storage implemented through AWS Lambda, EventBridge, and Amazon S3, producing a structured dataset of 23,556 observations and 75 variables. A LightGBM regression model forecasts short-term delay at two horizons (t+15 and t+30 minutes), while a two-stage multi-class classifier separates normal from congested traffic states and, within the congested subset, distinguishes slow traffic from jam conditions. Forecasts are translated into operational signal-control actions through a rule-based decision layer and evaluated in a SUMO/TraCI microscopic simulation environment against a fixed-time baseline, a max-pressure-style pressure-adaptive controller, a bridge-model hybrid controller, and an experimental Deep Q-Network (DQN) reinforcement-learning controller. Results show that LightGBM achieved R² = 0.82 and R² = 0.77 at the two forecasting horizons, while the two-stage classifier reached 90.6% overall accuracy. In simulation, the pressure-adaptive controller reduced mean waiting time by approximately 33.6% relative to the fixed-time baseline, while the DQN controller achieved an average reduction of approximately 23.3% across multiple random seeds. The proposed framework demonstrates a reproducible, data-driven pathway from real-time observation to adaptive traffic-signal decision-making, without removing engineering judgment from the control loop.
Downloads
References
Aslani, M., Mesgari, M. S., & Wiering, M. (2017). Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events. Transportation Research Part C: Emerging Technologies, 85, 732–752. https://doi.org/10.1016/j.trc.2017.09.020
Cai, C., Wong, C. K., & Heydecker, B. G. (2009). Adaptive traffic signal control using approximate dynamic programming. Transportation Research Part C: Emerging Technologies, 17(5), 456–474. https://doi.org/10.1016/j.trc.2009.04.005
Du, K., Guo, X., Li, L., Song, J., Shi, Q., Hu, M., & Fang, J. (2025). Traffic prediction in time series, spatial-temporal, and OD data: A systematic survey. Journal of Traffic and Transportation Engineering (English Edition), 12(3), 666–700. https://doi.org/10.1016/j.jtte.2025.03.001
Genders, W., & Razavi, S. (2016). Using a deep reinforcement learning agent for traffic signal control (arXiv:1611.01142). arXiv. https://arxiv.org/abs/1611.01142
Google for Developers. (2025a). Routes API overview. https://developers.google.com/maps/documentation/routes
Google for Developers. (2025b). Method: computeRouteMatrix | Routes API. https://developers.google.com/maps/documentation/routes/reference/rest/v2/TopLevel/computeRouteMatrix
Google for Developers. (2025c). Set the level of traffic data | Routes API. https://developers.google.com/maps/documentation/routes/config_trade_offs
Google for Developers. (2026). Method: computeRoutes | Routes API; Request route polylines. https://developers.google.com/maps/documentation/routes/reference/rest/v2/TopLevel/computeRoutes
Jing, P., Huang, H., & Chen, L. (2017). An adaptive traffic signal control in a connected vehicle environment: A systematic review. Information, 8(3), Article 101. https://doi.org/10.3390/info8030101
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30, 3146–3154.
Kurniawan, F., Agustian, H., Dermawan, D., Nurdin, R., Ahmadi, N., & Dinaryanto, O. (2025). Hybrid rule-based and reinforcement learning for urban signal control in developing cities: A systematic literature review and practice recommendations for Indonesia. Applied Sciences, 15(19), Article 10761. https://doi.org/10.3390/app151910761
Lopez, P. A., Behrisch, M., Bieker-Walz, L., Erdmann, J., Flötteröd, Y.-P., Hilbrich, R., Lücken, L., Rummel, J., Wagner, P., & Wießner, E. (2018). Microscopic traffic simulation using SUMO. In Proceedings of the 21st IEEE International Conference on Intelligent Transportation Systems (ITSC) (pp. 2575–2582). IEEE. https://doi.org/10.1109/ITSC.2018.8569938
Maadi, S., Stein, S., Hong, J., & Murray-Smith, R. (2022). Real-time adaptive traffic signal control in a connected and automated vehicle environment: Optimisation of signal planning with reinforcement learning under vehicle speed guidance. Sensors, 22(19), Article 7501. https://doi.org/10.3390/s22197501
Michailidis, P., Michailidis, I., Lazaridis, C. R., & Kosmatopoulos, E. (2025). Traffic signal control via reinforcement learning: A review on applications and innovations. Infrastructures, 10(5), Article 114. https://doi.org/10.3390/infrastructures10050114
Noaeen, M., Naik, A., Goodman, L., Crebo, J., Abrar, T., Hossein Abad, Z. S., Bazzan, A. L. C., & Far, B. (2022). Reinforcement learning in urban network traffic signal control: A systematic literature review. Expert Systems with Applications, 199, Article 116830. https://doi.org/10.1016/j.eswa.2022.116830
SUMO Documentation. (2026a). Traffic lights. https://sumo.dlr.de/docs/Simulation/Traffic_Lights.html
SUMO Documentation. (2026b). TraCI. https://sumo.dlr.de/docs/TraCI/index.html
SUMO Documentation. (2026c). TraCI4Traffic Lights tutorial. https://sumo.dlr.de/docs/Tutorials/TraCI4Traffic_Lights.html
A systematic literature review of traffic congestion forecasting: From machine learning techniques to large language models. (2025). Forecasting, 7(4), Article 142.
Tabatadze, B. (2026). AI-assisted programming in practice: Conceptual foundations and data-informed observations. Computational and Applied Science, 1(1), 84–100.
Varaiya, P. (2013). Max pressure control of a network of signalized intersections. Transportation Research Part C: Emerging Technologies, 36, 177–195.
