1. Proceedings
  2. I3M
  3. 2018
  4. MAS
  5. 10.46354/i3m.2018.mas.016

An agent-based model for robustness testing of freight train schedules

  • a Matthias Rößler , 
  • b Matthias Wastian  ,
  • c Michael Landsiedl , 
  • d Niki Popper  
  • a,b,c,d dwh GmbH, Neustiftgasse 57-59. 1070 Vienna, Austria
Cite as
Rößler M., Wastian M., Landsiedl M., Popper N. (2018). An agent-based model for robustness testing of freight train schedules. Proceedings of the 17th International Conference on Modeling & Applied Simulation (MAS 2018), pp. 101-105. DOI: https://doi.org/10.46354/i3m.2018.mas.016

Abstract

Optimization for train schedules of freight trains is extremely complex. Having a tight schedule is very efficient, but the impact of delays and cancellation rises and puts an environmentally sustainable and accurately timed supply of goods at risk. In order to address these issues, the Rail Cargo Austria commissioned a proof of concept that incorporates the optimization of train schedules with an agent-based model that tests the robustness of the optimized schedule against delays. Thereby the delays do not have to be incorporated into the optimization directly which would make the optimization problem even more complex and impossible to solve with classic techniques. Additionally, the use of historical data of freight train runs is integrated into the proof of concept and certain parameters for the simulation are gathered by data analysis and machine learning techniques. In this paper the agent-based model and a scenario to show its capabilities are presented.

References

  1. Barthélemy J., Carletti T., 2017. An adaptive agentbased approach to traffic simulation. Transportation Research Procedia, 25: 1238-1248.
  2. Cacchiani V., Caprara A., Galli L., Kroon L., Maróti G., Toth P., 2012. Railway Rolling Stock Planning: Robustness Against Large Disruptions. Transportation Science 46(2): 217-232.
  3. Cerreto F., 2015. Micro-simulation based analysis of railway lines robustness. Proceedings of the 6th International Conference on Railway Operations Modelling and Analysis, pp. 164-1 – 164-13. March 23-26, Narashino, Japan.
  4. Fernandes de Faria C.H., Monteiro da Costa Cruz M., 2017. Railway planning: an integrated approach using discrete event simulation. Proceedings of the International Conference on Harbor, Maritime and Multimodal Logistic Modelling and Simulation, pp. 148-156. September 18-20, Barcelona, Spain.
  5. Flier H.-F., 2011. Optimization of Railway Operations: Algorithms, Complexity, and Models. Dissertation. ETH Zurich.
  6. Geurts P., Ernst D., Wehenkel L., 2006. Extremely randomized trees. Machine Learning, 63(1):3-42.
  7. Guo C., Berkhahn F., 2016. Entity Embeddings of Categorical Variables. CoRR. http://arxiv.org/abs/1604.06737.
  8. Lindfeldt A., 2015. Railway capacity analysis – Methods for simulation and evaluation of timetables, delays and infrastructure. Dissertation. KTH Royal Institute of Technology, Stockholm.
  9. Ljubovic V., 2009. Traffic simulation using agent-based models. Proceedings of the XXII International Symposium on Information, Communication and Automation Technologies, pp. 1-6. October 29-31, Sarajevo, Bosnia and Herzegovina.
  10. Oneto L., Fumeo E., Clerico C., Canepa R., Papa F., Dambra C., Mazzino N., Anguita D., 2018. Train Delay Prediction Systems: A Big Data Analytics Perspective. Big Data Research 11: 54-64.
  11. Oneto L., Fumeo E., Clerico C., Canepa R., Papa F., Dambra C., Mazzino N., Anguita D., 2017.
    Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout. IEEE Transactions on Systems, Man, and Cybernetics: Systems 47(10): 2754-2767.
  12. Oneto L., Fumeo E., Clerico C., Canepa R., Papa F., Dambra C., Mazzino N., Anguita D., 2017.
    Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout. IEEE Transactions on Systems, Man, and Cybernetics: Systems 47(10): 2754-2767.
  13. Pouryousef H., Lautala P., 2015. Hybrid simulation approach for improving railway capacity and train schedules. Journal of Rail Transport Planning & Management 5.4: 211-224.
  14. Salgado D., Jolovic D., Martin P.T., Aldrete R.M.,2016. Traffic Microsimulation Models Assessment – A Case Study of International Land Port of Entry. Procedia Computer Science, 83:441-448.
  15. Wood S., 2012. Traffic microsimulation – dispelling the myths. Traffic Engineering and Control, 53(9): 339-344.
  16. Yaghini M., Khoshraftar M., Seyesabadi M., 2013. Railway passenger train delay prediction via neural network model. In Journal of Advanced Transportation, 47(3): 355-368.