Multivariable optimization of urban traffic through distributed intelligent control
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13881Keywords:
Integrated traffic management, Distributed optimisation for large-scale systems, Control over networks, Multi-agent system, Coordination of multiple vehicle systems, Networked embedded control systemsAbstract
This paper summarizes a research line aimed at intelligent urban traffic management through the transition from static controllers to multivariable distributed architectures.
It describes the development of the CICADA architecture, which integrates the simultaneous control of traffic lights, speed limits, turns, and parking using deep reinforcement learning and deontic logic to ensure normative safety.
Validations conducted in SUMO simulation environments demonstrate that coordinating these variables significantly reduces queues, travel times, and pollutant emissions, outperforming traditional monovariable approaches.
The proposed system establishes a scalable foundation for future connected and autonomous mobility in smart cities.
References
Abboud, K., Omar, H. A., Zhuang,W., 2016. Interworking of dsrc and celular network technologies for v2x communications: A survey. IEEE transactions on vehicular technology 65 (12), 9457–9470.
Chu, T., Wang, J., Codecà, L., Li, Z., 2019. Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE transactions on intelligent transportation systems 21 (3), 1086–1095.
Gartner, N. H., 1983. OPAC: A demand-responsive strategy for traffic signal control. No. 906.
Goodall, N. J., Smith, B. L., Park, B., 2013. Traffic signal control with connected vehicles. Transportation Research Record 2381 (1), 65–72.
Hunt, P., Robertson, D., Bretherton, R., Winton, R., 1981. Scoot-a traffic responsive method of coordinating signals. Tech. rep.
Iza, C., Iza, D., Posadas-Yagüe, J.-L., Poza-Lujan, J.-L., 2026a. Coordinated optimization of speed, parking, and turns in an integrated urban traffic system. Expert Systems with Applications 323, 132249. DOI: https://doi.org/10.1016/j.eswa.2026.132249
Iza, C., Iza, J., Posadas-Yagüe, J.-L., Poza-Lujan, J.-L., 2026b. Urban traffic optimization through traffic rule changes at intersections. In: Min-Allah, N., Alissa, K., Sitek, P., Sano, M., Rodr´ıguez, S., Nongaillard, A. (Eds.), Distributed Computing and Artificial Intelligence, 22nd International Conference. Springer Nature Switzerland, Cham, pp. 361–371.
Iza, C., Iza, J., Posadas-Yagüe, J.-L., Poza-Lujan, J.-L., Dec. 2025a. Integration of speed control and parking management in sumo for urban traffic optimization. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal 14, e33585. DOI: 10.14201/adcaij.33585
Iza, C., Uribe-Chavert, P., Posadas-Yag¨ue, J.-L., Poza-Lujan, J.-L., 2025b. A scalable control solution for traffic signal coordination for adaptable and responsiveness streets. In: Marreiros, G., Grande, L., Llerena, J. P., Conceicäo, L., Ko, H., Plaza, M., Ricca, M. (Eds.), Distributed Computing and Artificial Intelligence, Special Sessions II, 21st International Conference. Springer Nature Switzerland, Cham, pp. 272–278.
Iza Guzmán, C. F., 2023. Dispositivo de regulaci´on del tr´afico para optimizar el tr´ansito en intersecciones.
Lowrie, P., 1990. Scats, sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic.
Moreno-Malo, J., Posadas-Yagüe, J.-L., Cano, J. C., Calafate, C. T., Conejero, J. A., Poza-Lujan, J.-L., 2024. Improving traffic light systems using Deep q-networks. Expert Systems with Applications 252, 124178.
Oroojlooy, A., Nazari, M., Hajinezhad, D., Silva, J., 2020. Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Advances in Neural Information Processing Systems 33, 4079–4090.
Waheed, A., Krishna, P. V., Sadoun, B., Obaidat, M., et al., 2021. Learning automata and reservation based secure smart parking system: Methodology and simulation analysis. Simulation Modelling Practice and Theory 106, 102205.
Zhang, Y., Quinones-Grueiro, M., Zhang, Z., Wang, Y., Barbour, W., Biswas, G.,Work, D., 2023. Marvel: Multi-agent reinforcement-learning for largescale variable speed limits. arXiv preprint arXiv:2310.12359.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Cristian Iza, Juan-Luis Posadas-Yagüe, Miguel Rebollo, Jose-Luis Poza-Lujan
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
