The application of predictive control technologies аt intelligent transport systems

The article addresses pressing issues related to the use of machine learning and artificial intelligence methods in the design, deployment, and development of intelligent transport systems (ITS) in the Russian Federation, which are currently being implemented within the framework of the national project “Infrastructure for Life.” Particular attention is paid to the monitoring and traffic flow control tools currently in use, which constitute an integral part of such systems and ensure the achievement of their goals and objectives. The traditional toolkit for building intelligent transport systems, based on scenario-driven and local adaptive control of traffic signal controllers, makes it possible to obtain certain positive effects by reacting to emerging changes in parameters. However, the most promising is an approach based on predictive control of traffic flow parameters using network-wide adaptive control. This approach models the complex interdependencies between internal and external factors influencing traffic flows and the dynamics of the traffic situation. Models based on real traffic flow parameters make it possible to identify and estimate the probabilities of changes in these parameters, for example, to forecast the occurrence of congestion at a specific location and at a specific time. A predictive control approach, implemented as part of the enhancement of the functional capabilities of intelligent transport systems, will provide additional positive socio-economic effects for all road users.

1. Astarita V., Giofrè V.P., Guido G., Vitale A. A Scientometric-Based Review of Traffic Signal Control Methods and Experiments Based on Connected Vehicles and Floating Car Data (FCD), Appl. Sci., 2021, vol. 11, no. 5547, 18 p. – DOI: 10.3390/app11115547.

2. Zhang L., Khalgui M., Li Z. Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles, Sensors, 2021, vol. 21, no. 7330, 21 p. – DOI: 10.3390/s21187330.

3. Jafari S., Shahbazi Z., Byun Y.-C. Improving the Performance of Single-Intersection Urban Traffic Networks Based on a Model Predictive Controller, Sustainability, 2021, vol. 13, no. 5630, 16 p. – DOI: 10.3390/su13105630.

4. Evstigneev I.A. Osnovy sozdanija intellektual'nyh transportnyh sistem v gorodskih aglomeracijah Rossii (Fundamentals of creating intelligent transport systems in urban agglomerations of Russia), Mоscow, Pero, 2021, 294 p.

5. Reestr programmnogo obespecheniya: official website, available at: https://reestr.digital.gov.ru.

6. Andreev E.O.; Zhankaziev S.V.; Zyryanov V.V.; Pavlov A.S. T-Comm: Telekommunikacii i transport, 2024, no. 1, pp. 38-43, DOI 10.36724/2072-8735-2024-18-1-38-43.

7. Bazhina M.A. Vestnik YUURGU, 2023, no. 3, pp. 41-45. – DOI 10.14529/law230307. – EDN KOYNVF.

8. Kuznecov S.A.; Nikolaev V.A. T-Comm: Ekonomika i upravlenie, 2025, no. 31 (6), pp. 728-737. – DOI 10.35854/1998-1627-2025-6-728-737. – EDN RISOHW.

9. Syrcova E.A. T-Comm: Gosudarstvennoye upravleniye. Elektronnyy vestnik, 2023, no. 101, pp. 159-168. – DOI 10.24412/2070-1381-2023-101-159-169. – EDN RHWEOJ.