A two-stage road traffic congestion prediction and resource dispatching toward a self-organizing traffic control system

  • Zied Bouyahia
  • Hedi Haddad
  • Nafaa JabeurEmail author
  • Ansar Yasar
Original Article


Since decades, road traffic congestions have been recognized as an escalating problem in many metropolitan areas worldwide. In addition to causing substantial number of casualties and high pollution rates, these congestions are decelerating economic growth by reducing mobility of people and goods as well as increasing the loss of working hours and fuel consumption. In order to deal with this problem, extensive research works have successively focused on predicting road traffic jams and then predicting their propagations. In spite of their relevance, the proposed solutions to traffic jam propagation have been profoundly dependent on historical data. They have not also used their predictions to intelligently allocate traffic control resources accordingly. We, therefore, propose in this paper a new two-stage traffic resource dispatching solution which is ultimately aiming to implement a self-organizing traffic control system based on Internet of Things. Our solution uses in its first phase a Markov Random Field (MRF) to model and predict the spread of traffic congestions over a road network. According to the obtained predictions, the solution uses Markov Decision Process (MDP) to automatically allocate the road traffic resources. Our simulations are showing satisfactory results in terms of efficient intervention ratios compared to other solutions.


Markov random fields Markov decision process Road traffic congestion Traffic congestion prediction 



The authors are grateful to the anonymous reviewers for their constructive remarks and suggestions that have substantially improved the manuscript.


  1. 1.
    Djahel S, Jabeur N, Barrett R, Murphy J (2015) Toward V2I communication technology-based solution for reducing road traffic congestion in smart cities, Networks, Computers and Communications (ISNCC), 2015 International Symposium on, Hammamet, pp 1–6.
  2. 2.
    Wang G, Kim J (2016) The prediction of traffic congestion and incident on urban road networks using naive Bayes classifier. In: Australasian transport research forum 2016 proceedings. Melbourne, AustraliaGoogle Scholar
  3. 3.
    Florido E, Castaño O, Troncoso A, Martínez-Álvarez F (2015) Data mining for predicting traffic congestion and its application to Spanish data. In: Herrero Á, Sedano J, Baruque B, Quintián H, Corchado E (eds) 10th International Conference on Soft Computing Models in Industrial and Environmental Applications. Advances in intelligent systems and computing, vol 368. Springer, ChamGoogle Scholar
  4. 4.
    Li X, Zheng X, Guo W, Ren Y, Wang Y, Yang M (2013) Traffic accident propagation properties and control measures for urban links based on cellular automata. Adv Mech Eng 5:905640. Google Scholar
  5. 5.
    Rehborn H, Klenov SL, Palmer J (2011) An empirical study of common traffic congestion features based on traffic data measured in the USA, the UK, and Germany. Physica A 390(23–24):4466–4485Google Scholar
  6. 6.
    Schönhof M, Helbing D (2007) Empirical features of congested traffic states and their implications for traffic modeling. Transp Sci 41(2):135–166Google Scholar
  7. 7.
    Zhao J et al (2016) Spatio-temporal propagation of cascading overload failures in spatially embedded networks. Nat Commun 7Google Scholar
  8. 8.
    Fei W, Song G, Zhang F, Gao Y, Yu L (2017) Practical approach to determining traffic congestion propagation boundary due to traffic incidents. J Cent South Univy 24(2):413–422. Google Scholar
  9. 9.
    Jiang Y, Kang R, Li D, Guo S, Havlin S (2017) Spatio-temporal propagation of traffic jams in urban traffic networks. arXiv preprint arXiv:1705.08269Google Scholar
  10. 10.
    Xiong H, Vahedian A, Zhou X (2018) Predicting traffic congestion propagation patterns: a propagation graph approach. In 11th ACM SIGSPATIAL International Workshop on Computational Transportation Science (IWCTS’18), ACMGoogle Scholar
  11. 11.
    Nguyen H, Liu W, Chen F (2017) Discovering congestion propagation patterns in spatio-temporal traffic data. IEEE 3(2):169–118Google Scholar
  12. 12.
    Liu C, Zhang S, Wu H, Fu Q (2017) A dynamic spatiotemporal analysis model for traffic incident influence prediction on urban road networks. ISPRS Int J Geo-Inf 6:362Google Scholar
  13. 13.
    Pan B, Demiryurek U, Shahabi C, Gupta C (2013) Forecasting spatiotemporal impact of traffic incidents on road networks. In: ICDM, pp 587–596Google Scholar
  14. 14.
    Wang Z, Qi X, Jiang H (2018) Estimating the spatiotemporal impact of traffic incidents: an integer programming approach consistent with the propagation of shockwaves. Transp Res B 111(12):356–369Google Scholar
  15. 15.
    Leigh J, Dunnett S, Jackson L (2017) Predictive police patrolling to target hotspots and cover response demand. Ann Oper Res:1–16Google Scholar
  16. 16.
    Camacho-Collados M, Liberatore F (2015) A decision support system for predictive police patrolling. Decis Support Syst 75:25–37Google Scholar
  17. 17.
    Firooze S, Rafiee M, Zenouzzadeh SM (2018) An optimization model for emergency vehicle location and relocation with consideration of unavailability time. Sci Iran 25(6):3685–3699Google Scholar
  18. 18.
    Enayati S, Mayorga ME, Rajagopalan HK, Saydam C (2018) Real-time ambulance redeployment approach to improve service coverage with fair and restricted workload for EMS providers. Omega 79:67–80Google Scholar
  19. 19.
    Cabral ELDS, Castro WRS, Florentino DRDM, Viana DDA, Costa Junior JFD, Souza RPD, Medeiros AC (2018) Response time in the emergency services. Systematic review. Acta Cir Bras 33(12):1110–1121Google Scholar
  20. 20.
    Brotcorne L, Laporte G, Semet F (2003) Ambulance location and relocation models. Eur J Oper Res 147(3):451–463MathSciNetzbMATHGoogle Scholar
  21. 21.
    Villarreal B, Garza-Reyes JA, Granda-Gutiérrez E, Kumar V, Lankenau-Delgado S (2018) A lean transportation approach for improving emergency medical operations. Prod Plan Control 29(11):928–942Google Scholar
  22. 22.
    Li X, Zhao Z, Zhu X, Wyatt T (2011) Covering models and optimization techniques for emergency response facility location and planning: a review. Math Methods Oper Res 74(3):281–310MathSciNetzbMATHGoogle Scholar
  23. 23.
    Schmid V (2012) Solving the dynamic ambulance relocation and dispatching problem using approximate dynamic programming. Eur J Oper Res 219(3):611–621MathSciNetzbMATHGoogle Scholar
  24. 24.
    Aringhieri R, Bruni ME, Khodaparasti S, Van Essen JT (2017) Emergency medical services and beyond: addressing new challenges through a wide literature review. Comput Oper Res 78:349–368MathSciNetzbMATHGoogle Scholar
  25. 25.
    Majzoubi F, Bai L, Heragu SS (2012) An optimization approach for dispatching and relocating EMS vehicles. IIE Trans Healthc Syst Eng 2(3):211–223Google Scholar
  26. 26.
    Adler N, Hakkert AS, Kornbluth J, Raviv T, Sher M (2014) Location-allocation models for traffic police patrol vehicles on an interurban network. Ann Oper Res 221(1):9–31zbMATHGoogle Scholar
  27. 27.
    Wheeler AP (2018) Creating optimal patrol areas using the P-median model. Policing.
  28. 28.
    Curtin KM, Hayslett-McCall K, Qiu F (2010) Determining optimal police patrol areas with maximal covering and backup covering location models. Netw Spat Econs 10(1):125–145MathSciNetzbMATHGoogle Scholar
  29. 29.
    Dunnett S, Leigh J, Jackson L (2018) Optimising police dispatch for incident response in real time. J Oper Res Soc 70:269–279. Google Scholar
  30. 30.
    Ren X, Zhu J, Huang J (2012) Multi-period dynamic model for emergency resource dispatching problem in uncertain traffic network. Syst Eng Procedia 5:37–42Google Scholar
  31. 31.
    Reis D, Melo A, Coelho AL, Furtado V (2006) Towards optimal police patrol routes with genetic algorithms. In: International Conference on Intelligence and Security Informatics. Springer, Berlin, pp 485–491Google Scholar
  32. 32.
    He Y, Liu Z, Shi J, Wang Y, Zhang J, Liu J (2015) K-shortest-path-based evacuation routing with police resource allocation in city transportation networks. PLoS One 10(7):e0131962Google Scholar
  33. 33.
    Hajibabai L, Saha D (2019) Patrol route planning for incident response vehicles under dispatching station scenarios. Comput Aided Civ Inf Eng 34(1):58–70Google Scholar
  34. 34.
    Leigh JM, Jackson LM, Dunnett SJ (2016) Police officer dynamic positioning for incident response and community presence. Proceedings of the 5th International Conference on Operations Research and Enterprise Systems (ICORES 2016), pp 261–270Google Scholar
  35. 35.
    Mukhopadhyay A, Zhang C, Vorobeychik Y, Tambe M, Pence K, Speer P (2016) Optimal allocation of police patrol resources using a continuous-time crime model. In: International Conference on Decision and Game Theory for Security. Springer, Cham, pp 139–158Google Scholar
  36. 36.
    Zografos KG, Androutsopoulos KN, Vasilakis GM (2002) A real-time decision support system for roadway network incident response logistics. Transp Res C 10(1):1–18Google Scholar
  37. 37.
    Silva F, Serra D (2016) Locating emergency services with different priorities: the priority queuing covering location problem. In: Operational research for emergency planning in healthcare, vol 1. Palgrave Macmillan, London, pp 15–35Google Scholar
  38. 38.
    Li S, Keskin BB (2014) Bi-criteria dynamic location-routing problem for patrol coverage. J Oper Res Soc 65(11):1711–1725Google Scholar
  39. 39.
    Ozbay K, Xiao W, Iyigun C, Gursoy M (2013) Probabilistic programming models for response vehicle dispatching and resource allocation in traffic incident management. J Ann Oper Res 203(1):389–406. zbMATHGoogle Scholar
  40. 40.
    Duan X, Song S, Zhao J (2015, Article ID 731492, 12 pages, 2015) Emergency vehicle dispatching and redistribution in highway network based on bilevel programming. Math Probl Eng.
  41. 41.
    Raiyn J (2017) Road traffic congestion management based on search allocation approach. Transp Telecommun 18(1):25–33Google Scholar
  42. 42.
    Brown M, Saisubramanian S, Varakantham P, Tambe M (2014) Streets: game-theoretic traffic patrolling with exploration and exploitation. In: Proceedings of the Twenty Sixth Conference on Innovative Applications of Artificial Intelligence (IAAI), July 2014Google Scholar
  43. 43.
    Wilson RE (2008) Mechanisms for spatio-temporal pattern formation in highway traffic models. Philos Trans R Soc A Math Phys Eng Sci 366(1872):2017–2032MathSciNetzbMATHGoogle Scholar
  44. 44.
    Orosz G, Wilson RE, Szalai R, Stépán G (2009) Exciting traffic jams: nonlinear phenomena behind traffic jam formation on highways. Phys Rev E 80(4 Pt 2):046205Google Scholar
  45. 45.
    Treiber M, Kesting A, Helbing D (2010) Three-phase traffic theory and two-phase models with a fundamental diagram in the light of empirical stylized facts. Transp Res B Methodol 44(8–9):983–1000Google Scholar
  46. 46.
    Helbing D, Treiber M, Kesting A, Schönhof M (2009) Theoretical vs. empirical classification and prediction of congested traffic states. Eur Phys J B 69(4):583–598Google Scholar
  47. 47.
    Ma G, Zheng C, Wan X (2017) Determination of the scope of traffic incident. Adv Mech Eng 9(8):1687814017717184Google Scholar
  48. 48.
    Karyotis V (2017) A Markov random field framework for modeling malware propagation in complex communications networks. IEEE Trans Dependable Secure Comput 11Google Scholar
  49. 49.
    Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8(3–4):279–292zbMATHGoogle Scholar
  50. 50.
    Meyn SP (1997 Dec) The policy iteration algorithm for average reward Markov decision processes with general state space. IEEE Trans Autom Control 42(12):1663–1680MathSciNetzbMATHGoogle Scholar
  51. 51.
    Acar P, Sundararaghavan V (2016) A Markov random field approach for modeling spatio-temporal evolution of microstructures. Model Simul Mater Sci Eng 24(7):075005Google Scholar
  52. 52.
    Barker SA, Rayner PJ (2000) Unsupervised image segmentation using Markov random field models. Pattern Recogn 33(4):587–602Google Scholar
  53. 53.
    Wang P, Li Y, Reddy CK (2017) Machine learning for survival analysis: a survey. arXiv preprint arXiv:1708.04649Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Zied Bouyahia
    • 1
  • Hedi Haddad
    • 1
  • Nafaa Jabeur
    • 2
    Email author
  • Ansar Yasar
    • 3
  1. 1.Computer Science DepartmentDhofar UniversitySalalahSultanate of Oman
  2. 2.German University of Technology in Oman (GUtech)MuscatSultanate of Oman
  3. 3.Transportation Research Institute (IMOB)Hasselt UniversityDiepenbeekBelgium

Personalised recommendations