Іntelligent adaptive bus route management based on real-time passenger flow forecasting
DOI:
https://doi.org/10.33216/1998-7927-2026-304-6-170-185Keywords:
information technology, adaptive management, urban bus transportation, passenger flow forecasting, dispatch decisions, public transportAbstract
The article develops an organizational and methodological approach to intelligent adaptive management of an urban bus route based on real-time passenger flow forecasting. The relevance of the study is determined by the need to improve the quality of public transport services under conditions of uneven demand, changing traffic situations, intraday fluctuations in route loading, and limited carrier resources. Unlike traditional approaches, which rely mainly on averaged or retrospective data, the proposed approach focuses on combining current route monitoring with short-term demand forecasting and the formation of proactive dispatching decisions. This makes it possible to consider the route not as a static system with fixed parameters, but as a controllable object whose state constantly changes under the influence of passenger demand, road conditions, trip duration, and vehicle availability.
The purpose of the study is to develop an approach that ensures the coordination of transport service quality indicators with the requirements of operational stability and the economic feasibility of carrier operations. The study forms a system of interrelated indicators covering actual and forecast passenger flow, headway, vehicle occupancy rate, average passenger waiting time, service regularity, revenue, costs, and financial result. The use of spatio-temporal passenger flow forecasting, rules for determining the required number of buses, adaptive headway, and the choice of control action with stability verification is substantiated. In addition, the possibility of adjusting the type of rolling stock depending on the expected level of demand, the permissible level of vehicle occupancy, and the carrier’s resource constraints is taken into account.
The results of the study show that the proposed approach makes it possible to formalize the transition from reactive to proactive bus route management, promptly identify risks of vehicle overcrowding, reduce expected passenger waiting time, and account for the carrier’s financial constraints. The proposed decision-making logic involves comparing forecast load with permissible capacity, assessing the impact of headway changes on service regularity, and verifying the economic result before implementing a control action. Particular attention is paid to the possibility of using GPS monitoring data, automated passenger counting, and electronic ticketing to update model parameters in real time, refine demand estimates at individual stops, identify critical overload periods, and improve forecast reliability. The practical significance of the study lies in the possibility of applying the results in dispatching management systems, digital transport monitoring platforms, and information-analytical decision support modules in the field of urban passenger transport. The obtained results may serve as a methodological basis for further testing on actual urban route data, comparing alternative dispatching response scenarios, and developing intelligent transport systems in cities with different levels of passenger demand.
References
1. Hörcher D., Tirachini A. A review of public transport economics. Economics of Transportation. 2021. Vol. 25. Article 100196. DOI: https://doi.org/10.1016/j.ecotra.2021.100196
2. Time-dependent transit fare optimization with elastic and spatially distributed demand / Q. Guo, L. Sun, P. Schonfeld, Z. Li. Transportation Research Part A: Policy and Practice. 2021. Vol. 148. P. 353–378. DOI: https://doi.org/10.1016/j.tra.2021.04.002
3. Bertsimas D., Ng Y. S., Yan J. Joint frequency-setting and pricing optimization on multimodal transit networks at scale. Transportation Science. 2020. Vol. 54, no. 3. P. 839–853. DOI: https://doi.org/10.1287/trsc.2019.0959
4. Tian Q., Wang D. Z. W., Lin Y.-H. Service operation design in a transit network with congested common lines. Transportation Research Part B: Methodological. 2021. Vol. 143. P. 54–85. DOI: https://doi.org/10.1016/j.trb.2020.12.003
5. Petit A., Lei C., Ouyang Y. Multiline bus bunching control via vehicle substitution. Transportation Research Part B: Methodological. 2019. Vol. 126. P. 247–269. DOI: https://doi.org/10.1016/j.trb.2019.05.009
6. Robust dynamic bus controls considering delay disturbances and passenger demand uncertainty / S. Li, R. Liu, L. Yang, Z. Gao. Transportation Research Part B: Methodological. 2019. Vol. 125. P. 277–308. DOI: https://doi.org/10.1016/j.trb.2019.03.019
7. Robust control for regulating frequent bus service on a dedicated bus lane / E. van der Werff, O. Cats, S. Hoogendoorn, H. van Lint. Transportation Research Record. 2019. Vol. 2673, no. 8. P. 139–149. DOI: https://doi.org/10.1177/0361198119845893
8. Iliopoulou C. A., Kepaptsoglou K., Vlahogianni E. Identifying spatio-temporal patterns of bus bunching in urban networks. Journal of Intelligent Transportation Systems. 2020. Vol. 24, no. 4. P. 365–378. DOI: https://doi.org/10.1080/15472450.2020.1722949
9. Drabicki A., Kucharski R., Cats O. Mitigating bus bunching with real-time crowding information. Transportation. 2023. Vol. 50. P. 1901–1927. DOI: https://doi.org/10.1007/s11116-022-10270-3
10. Deep reinforcement learning-based holding control for bus bunching considering passenger waiting perception / D. Liu, M. Zhou, H. Wang, J. Li. Sustainability. 2023. Vol. 15, no. 14. Article 10947. DOI: https://doi.org/10.3390/su151410947
11. Wang J., Sun L. Multi-objective multi-agent deep reinforcement learning to reduce bus bunching and passenger waiting time. Transportation Research Part C: Emerging Technologies. 2023. Vol. 153. Article 104309. DOI: https://doi.org/10.1016/j.trc.2023.104309
12. Rezazada M., Tirachini A., Cats O. Bus bunching: A comprehensive review and future research agenda. Transport Reviews. 2024. Vol. 44, no. 3. P. 421–451. DOI: https://doi.org/10.1080/01441647.2024.2313969
13. Lin X., Zhao J., Wilson N. H. M. Bunching-proof capabilities of modular buses. Transportation Science. 2024. Vol. 58, no. 1. P. 150–170. DOI: https://doi.org/10.1287/trsc.2023.0224
14. Zheng H., Liu T., Chen A. Alternative service network design for bus systems responding to time-varying road disruptions. Transportation Research Part B: Methodological. 2024. Vol. 181. Article 103042. DOI: https://doi.org/10.1016/j.trb.2024.103042
15. Dynamic scheduling of flexible bus services with hybrid requests and fairness concerns / W. Wu, C. Ma, R. Song et al. Transportation Research Part B: Methodological. 2024. Vol. 182. Article 103069. DOI: https://doi.org/10.1016/j.trb.2024.103069
16. Sangveraphunsiri T., Cassidy M. J., Daganzo C. F. Jitney-lite: A flexible-route feeder service for higher-ridership suburban transit systems. Transportation Research Part B: Methodological. 2022. Vol. 157. P. 245–269. DOI: https://doi.org/10.1016/j.trb.2021.12.015
17. Optimal design of community shuttles considering demand response and route choice / J. Xiong, X. Qian, Y. Zhang et al. Transportation Research Part C: Emerging Technologies. 2021. Vol. 131. Article 103109. DOI: https://doi.org/10.1016/j.trc.2021.103109
18. Dou Y., Zhou J., Zhang M. Customized bus service design for uncertain commuting travel demand. Transportmetrica A: Transport Science. 2021. Vol. 17, no. 3. P. 197–219. DOI: https://doi.org/10.1080/23249935.2020.1864509
19. Zhou Y., Meng Q., Ong G. P. Electric bus charging scheduling for a single public transport route with dynamic electricity prices. Transportation Research Part B: Methodological. 2022. Vol. 159. P. 63–89. DOI: https://doi.org/10.1016/j.trb.2022.03.002
20. Zhou Y., Ong G. P., Meng Q. Electric bus charging facility planning with uncertainties in operation. Transportation Research Part C: Emerging Technologies. 2023. Vol. 149. Article 104108. DOI: https://doi.org/10.1016/j.trc.2023.104108
21. Fei F., Yang H., Liu Z. Exploring the profitability of using electric bus fleets for transport and power grid services. Transportation Research Part C: Emerging Technologies. 2023. Vol. 148. Article 104060. DOI: https://doi.org/10.1016/j.trc.2023.104060
22. Collaborative optimization of electric bus line scheduling with multiple charging modes / D.-F. Xie, J.-Y. Wang, C. Lu et al. Transportation Research Part D: Transport and Environment. 2023. Vol. 114. Article 103551. DOI: https://doi.org/10.1016/j.trd.2022.103551
23. Cheng X., Nie Y., Lin J. An autonomous modular public transit service. Transportation Research Part C: Emerging Technologies. 2024. Vol. 160. Article 104746. DOI: https://doi.org/10.1016/j.trc.2024.104746
24. Ma H., Yang M., Li X. Integrated optimization of customized bus routes and timetables considering commuter heterogeneity. Computers & Industrial Engineering. 2023. Vol. 175. Article 108886. DOI: https://doi.org/10.1016/j.cie.2022.108886
25. Multi-depot vehicle scheduling with multiple vehicle types on overlapped bus routes / H. Shang, J. Xu, Y. Wang et al. Expert Systems with Applications. 2023. Vol. 227. Article 120352. DOI: https://doi.org/10.1016/j.eswa.2023.120352
26. Andrade-Michel G., Ceder A., Muñoz J. C. Vehicle and reliable driver scheduling for public bus transportation systems. Transportation Research Part B: Methodological. 2021. Vol. 150. P. 249–272. DOI: https://doi.org/10.1016/j.trb.2021.01.011
27. Boyer V., El Moudni A., Mes M. Vehicle and crew scheduling for flexible bus transportation systems. Transportation Research Part B: Methodological. 2018. Vol. 111. P. 99–118. DOI: https://doi.org/10.1016/j.trb.2018.04.008
28. Carosi S., Gallo G., Montemanni R. A matheuristic for integrated timetabling and vehicle scheduling. Transportation Research Part B: Methodological. 2019. Vol. 127. P. 99–124. DOI: https://doi.org/10.1016/j.trb.2019.07.004
29. Wood J., Yu Z., Gayah V. V. Development and evaluation of frameworks for realtime bus passenger occupancy prediction. International Journal of Transportation Science and Technology. 2023. Vol. 12, no. 2. P. 399–413. DOI: https://doi.org/10.1016/j.ijtst.2022.03.005
30. Bus-passenger-flow prediction model based on WPD, attention mechanism, and Bi-LSTM / Y. Pei, S. Ran, W. Wang, C. Dong. Sustainability. 2023. Vol. 15, no. 20. Article 14889. DOI: https://doi.org/10.3390/su152014889
31. Zhai X., Shen Y. Short-term bus passenger flow prediction based on graph diffusion convolutional recurrent neural network. Applied Sciences. 2023. Vol. 13, no. 8. Article 4910. DOI: https://doi.org/10.3390/app13084910
32. Real-time bus departure prediction using neural networks for smart IoT public bus transit / N. Rashvand, S. S. Hosseini, M. Azarbayjani, H. Tabkhi. IoT. 2024. Vol. 5, no. 4. P. 650–665. DOI: https://doi.org/10.3390/iot5040029
33. Lee C., Yoon Y. A novel bus arrival time prediction method based on spatiotemporal flow centrality analysis and deep learning. Electronics. 2022. Vol. 11, no. 12. Article 1875. DOI: https://doi.org/10.3390/electronics11121875
34. Ghandeharioun Z., Zendehdel Nobari P., Wu W. Exploring deep learning approaches for short-term passenger demand prediction. Data Science for Transportation. 2023. Vol. 5. Article 19. DOI: https://doi.org/10.1007/s42421-023-00075-w
35. Evaluation of urban bus service reliability on variable time horizons using a hybrid deep learning method / T. Zhou, W. Wu, L. Peng, X. Wu, C. Jiao, J. Sun. Reliability Engineering & System Safety. 2022. Vol. 220. Article 108090. DOI: https://doi.org/10.1016/j.ress.2021.108090
36. Passenger flow prediction for citywide bus stops based on gated multi-graph convolutional network / Y.-Y. Wang, C. Zhang, W.-P. Qu, Z.-H. Jiang. Journal of Intelligent Transportation Systems. 2025. Advance online publication. DOI: https://doi.org/10.1080/15472450.2025.2543820
