Public Transport

, Volume 2, Issue 3, pp 249–268 | Cite as

Real-time train driver rescheduling by actor-agent techniques

  • Erwin J. W. Abbink
  • David G. A. Mobach
  • Pieter J. Fioole
  • Leo G. Kroon
  • Eddy H. T. van der Heijden
  • Niek J. E. Wijngaards
Open Access
Original Paper

Abstract

Passenger railway operations are based on an extensive planning process for generating the timetable, the rolling stock circulation, and the crew duties for train drivers and conductors. In particular, crew scheduling is a complex process.

After the planning process has been completed, the plans are carried out in the real-time operations. Preferably, the plans are carried out as scheduled. However, in case of delays of trains or large disruptions of the railway system, the timetable, the rolling stock circulation and the crew duties may not be feasible anymore and must be rescheduled.

This paper presents a method based on multi-agent techniques to solve the train driver rescheduling problem in case of a large disruption. It assumes that the timetable and the rolling stock have been rescheduled already based on an incident scenario. In the crew rescheduling model, each train driver is represented by a driver-agent. A driver-agent whose duty has become infeasible by the disruption starts a recursive task exchange process with the other driver-agents in order to solve this infeasibility. The task exchange process is supported by a route-analyzer-agent, which determines whether a proposed task exchange is feasible, conditionally feasible, or not feasible. The task exchange process is guided by several cost parameters, and the aim is to find a feasible set of duties at minimal total cost.

The train driver rescheduling method was tested on several realistic disruption instances of Netherlands Railways (NS), the main operator of passenger trains in the Netherlands. In general the rescheduling method finds an appropriate set of rescheduled duties in a short amount of time. This research was carried out in close cooperation by NS and the D-CIS Lab.

Keywords

Multiagent System Team Leader Crew Schedule Rail Network Train Driver 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. Abbink EJW, Fischetti M, Kroon LG, Timmer G, Vromans MJCM (2005) Re-inventing crew scheduling at Netherlands railways. Interfaces 35(5):393–401 CrossRefGoogle Scholar
  2. Abbink EJW, Mobach DGA, Fioole PJ, Kroon LG, Wijngaards NJE, van der Heijden EHT (2008) Actor-agent based approach to train driver rescheduling. In: Proceedings of the 20th Belgian-Dutch conference on artificial intelligence (BNAIC 2008), Bad Boekelo, pp 1–8 Google Scholar
  3. Abbink EJW, Mobach DGA, Fioole PJ, Kroon LG, van der Heijden EHT, Wijngaards NJE (2009) Actor-agent application for train driver rescheduling. In: Proceedings of the eighth international conference on autonomous agents and multiagent systems, Budapest, pp 513–520 Google Scholar
  4. Helsinger A, Thome M, Wright T (2004) Cougaar: A Scalable, Distributed multi-agent architecture. In: Proceedings of the international conference on systems, man and cybernetics, The Netherlands Google Scholar
  5. Iacob SM, Nieuwenhuis CHM, Wijngaards NJE, Pavlin G, Van Veelen JB (2009) Actor-agent communities: design approaches. In: Papadopoulos, G.A, Badica, C. (eds) Intelligent distributed computing III, SCI, vol 237, pp 237–242 CrossRefGoogle Scholar
  6. Jiang Z, Xie C (2009) Multi-agent delay simulation model in mass rail transit system. In: International conference on measuring technology and mechatronics automation, Icmtma, vol 3, pp 717–720 CrossRefGoogle Scholar
  7. Kroon LG, Huisman D, Abbink EJW, Fioole PJ, Fischetti M, Maróti G, Schrijver A, Steenbeek A, Ybema R (2008) The new dutch timetable: the OR revolution. Interfaces 39(1):6–17 CrossRefGoogle Scholar
  8. Mao X, ter Mors A, Roos N, Witteveen C (2007) Coordinating competitive agents in dynamic airport resource scheduling. In: Petta P, Mueller JP, Klusch M, Georgeff M (eds) Proceedings of the 5th German conference on multiagent system technologies, LNAI, vol 4687, pp 133–144. Springer, Berlin Google Scholar
  9. Mobach DGA, Abbink EJW, Fioole PJ, Lentink RM, Kroon LG, van der Heijden EHT, Wijngaards NJE (2009) Train driver rescheduling using task-exchange teams. In: Proceedings of the second international workshop on: optimisation in multi-agent systems (OPTMAS) at AAMAS 2009 Google Scholar
  10. Potthoff D, Huisman D, Desaulniers G (2010) Column generation with dynamic duty selection for railway crew rescheduling. Transp Sci. doi: 10.1287/trsc.1100.0322
  11. Rezanova NJ, Ryan DM (2010) The train driver recovery problem—a set partitioning based model and solution method. Comput Oper Res 37(5), 845–856 CrossRefGoogle Scholar
  12. Shibghatullah AS, Eldabi T, Rzevski G (2006) A framework for crew scheduling management system using multi-agents system. In: 28th international conference on information technology interfaces (ITI 2006), Cavtat, Croatia Google Scholar
  13. Tranvouez E, Ferrarini A (2006) Multiagent modelling of cooperative disruption management in supply chains. In: International conference on service systems and service management, Troyes, pp 853–858 CrossRefGoogle Scholar
  14. Veelenturf LP, Potthoff D, Huisman D, Kroon LG (2009) Railway crew rescheduling with retiming. Report EI2009-24, Econometric Institute, Erasmus University Rotterdam, 24 p (Forthcoming in: Transp Res Part C) Google Scholar
  15. Walker CG, Snowdon JN, Ryan DM (2005) Simultaneous disruption recovery of a train timetable and crew roster in real-time. Comput Oper Res 32(8):2077–2094 CrossRefGoogle Scholar

Copyright information

© The Author(s) 2010

Authors and Affiliations

  • Erwin J. W. Abbink
    • 1
  • David G. A. Mobach
    • 2
  • Pieter J. Fioole
    • 1
  • Leo G. Kroon
    • 1
    • 3
  • Eddy H. T. van der Heijden
    • 2
  • Niek J. E. Wijngaards
    • 2
  1. 1.NSR Logistics InnovationNetherlands RailwaysUtrechtNetherlands
  2. 2.Thales Research & Technology NLD-CIS LabDelftNetherlands
  3. 3.Erasmus University RotterdamRotterdam School of ManagementRotterdamNetherlands

Personalised recommendations