Development of method for adaptive traffic light control at urban intersections based on vehicle navigation data

Introduction. Under conditions of sustained growth in motorization and increased loads in urban road networks of large cities, there is a need to improve control methods for signalized intersections. Traditional traffic signal control systems based on fixed timing plans or data obtained from local detectors demonstrate limited adaptability and do not always ensure efficient distribution of intersection capacity under variable traffic flow conditions. The purpose of this study is to develop a method for adaptive traffic signal control at urban intersections based on vehicle navigation data.
Materials and Methods. The study uses data obtained from vehicle navigation devices, including coordinates, speed, and direction of movement. The proposed methodology is based on forecasting the expected number of vehicles approaching an intersection from each traffic direction and estimating their arrival times. Traffic signal control parameters are adjusted within discrete calculation intervals of 15 minutes, taking into account the temporal uncertainty of vehicle arrivals. To improve control stability, a weighting mechanism is introduced, leading to correct record of vehicles arriving within the calculation intervals, as well as residual queues from previous periods.
Results. The results of the study have demonstrated that the application of the proposed method ensures a more balanced distribution of green signal timing in proportion to the expected load of traffic directions, which contributes to increased intersection capacity and reduced vehicle delays. The proposed approach is intended for use within governmental traffic management systems and does not require the installation of additional detectors or video surveillance equipment.
Discussion and conclusion. The practical significance of the study lies in the possibility of implementing the developed method in the design and modernization of traffic signal control systems in large cities. The research novelty refers to the application of a forecast-oriented approach to adaptive traffic signal control based on navigation data, which expands the capabilities of existing traffic control systems.

1. Reshetnikov E.B., Abramova L.S., Chernobaev N.S., Shirin V.V. Analysis of traffic organization in the central part of Kharkov city. Vestnik of Kharkiv National Automobile and Highway University. 2005; (29), 116–122. (In Russ.)

2. Vorobyev A.I., Zamytskih A.V., Golubchenko N.S., Vorobyeva T.V., Morozov D.Y. Ensuring the Accuracy of Digital Road Model Data to Increase Situational Awareness. Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex (TIRVED), Moscow, Russian Federation, 2021; pp. 1-6, doi: 10.1109/TIRVED53476.2021.9639134

3. Sargsyan A.T. Traffic situation in Yerevan and ways to modernize with the help of current problem of traffic congestion.The Russian Automobile and Highway Industry Journal. 2024;21(3):422-434. (In Russ.) DOI: 10.26518/2071-7296-2024-21-3-422-434. EDN: UAXSCA

4. Alamir H.S., Zargaryan E.V., Zargaryan, Yu.A. Intelligent system for controlling traffic congestion using a supervised machine learning algorithm based on adaptive IOTN. Izvestiya of Southern Federal University. Technical Sciences, 2023; (2(232)), 175–186. (In Russ.) DOI: 10.18522/2311-3103-2023-2-175-186

5. Romanowska A, Jamroz K. Comparison of Traffic Flow Models with Real Traffic Data Based on a Quantitative Assessment. Applied Sciences. 2021; 11(21): 9914. DOI: 10.3390/app11219914

6. Lozovaya E.A., Tereshkina O.A., Vlasova, O.I. Method for calculating the capacity of vehicles on a section of Aksaysky Prospekt in Rostov-on-Don. Fundamental Scientific Research: Theoretical and Practical Aspects, 2017; pp. 337–339. (In Russ.)

7. Zhang J., Wang F., Wang K., Lin W., Xu X., Chen C. Data-Driven Intelligent Transportation Systems: A Survey. IEEE Transactions on Intelligent Transportation Systems, 2011; Vol. 12, No. 4, pp. 1624-1639. doi:10.1109/TITS.2011.2158001

8. Xing Z, Huang M, Peng D. Overview of machine learning-based traffic flow prediction. Digital Transportation and Safety. 2023; 2(3):164−175 DOI: 10.48130/DTS-2023-0013

9. Singh G, Al’Aref SJ, Van Assen M, et al. Machine learning in cardiac CT: Basic concepts and contemporary data. J Cardiovasc Comput Tomogr. 2018; 12(3):192-201. doi:10.1016/j.jcct.2018.04.010

10. Ahsan M.M., Luna S.A., Siddique Z. Machine-Learning-Based Disease Diagnosis: A Comprehensive Review. Healthcare, 2022; 10(3), 541. DOI: 10.3390/healthcare10030541

11. Esteban Zimányi, Mahmoud Sakr, Arthur Lesuisse. MobilityDB: A Mobility Database Based on PostgreSQL and PostGIS. ACM Trans. Database Syst. 2020; 45, 4, Article 19 (December 2020), 42 pages. DOI: 10.1145/3406534

12. Alibieva Zh., Mukazhanov N., Cherikbaeva L., Yerimbetova, A., & Baiymbetov, D. (2024). Comparison of capabilities of NoSQL columnar database. Vestnik KazATK, 131(2), 350–358. (In Russ.) DOI: 10.52167/1609-1817-2024-131-2-350-358

13. Tsvetkov V.Ya. Geoinformation monitoring. Izvestiya of Higher Educational Institutions. Geodesy and Aerial Photography, 2005; (5), 151–155. (In Russ.)

14. Okhotnikov A. L. Geoinformation monitoring of transport objects. Science and Technology of Railways, 2017; 3(3), 35–47. (In Russ.)

15. Sargsyan A. Development of investment methods for remote combined traffic control in Yerevan city. Scientific Works of the National University of Architecture and Construction of Armenia, 2024; 89(2), 104–109. (In Russ.) DOI: 10.54338/18294200-2024.2-12

16. Sargsyan A. Study and analysis of the main transport problems in Yerevan city with the aim of improvement. Scientific Works of the National University of Architecture and Construction of Armenia, 2024; 89(2), 94–103. (In Russ.) DOI: 10.54338/18294200-2024.2-11

17. Yusuf J.A. Economic Evaluation of Smart Traffic Management Systems in Reducing Carbon Emissions. Journal of Economics, Business, and Commerce, 2024; 1(1), 30-35. DOI: 10.69739/jebc.v1i1.82

18. Goroshko V.S., Shamlytskyi, Ya.I. Application of adaptive traffic control systems. Actual Problems of Aviation and Cosmonautics, 2012; (8), 243–244. (In Russ.)

19. Danilchik R.A. Influence of adaptive systems on road traffic conditions. In Proceedings of the Student Scientific Conference “Science Week – 2015” . 2015; (p. 15). Brest State Technical University (BrSTU). (In Russ.)

20. Tkacheva T.M., Tsibalov K.A., Shishkin D.O. Errors of video camera, speedometer and navigator. Automobile. Road. Infrastructure, 2019; 1(19), 17. (In Russ.)

21. Boyarshinov M.G., Vavilin A.S. Patterns of traffic congestion indicator at some intersections of the road network. Intellekt. Innovacii. Investicii. 2024; Vol. 1, pp. 95–115. DOI: 10.25198/2077-7175-2024-1-95