Abstract
Determining the maximum capacities of shunting yards is an important problem at Dutch Railways (NS). Solving this capacity determination problem is computational expensive as it requires to solve an NP-hard shunting planning problem. Currently, NS uses a shunt plan simulator where a local search heuristic is implemented to determine such capacities.
In this paper, we study how to combine machine learning with local search in order to speed up finding shunting plans in the capacity determination problem. We investigate this in the following two ways. In the first approach, we propose to use the Deep Graph Convolutional Neural Network (DGCNN) to predict whether local search will find a feasible shunt plan given an initial solution. Using instances generated from the simulator, we build a classification model and show our approach can significantly reduce the simulation time in determining the capacity of a given shunting yard.
In the second approach, we investigate whether we can use machine learning to help local search decide which promising areas to explore during search. Therefore, DGCNN is applied to predict the order of search operators in which the local search heuristic should evaluate. We show that accurately predicting the evaluation order could find improved solutions faster, and may lead to more consistent plans.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Boysen, N., Fliedner, M., Jaehn, F., Pesch, E.: Shunting yard operations: theoretical aspects and applications. Eur. J. Oper. Res. 220(1), 1–14 (2012)
van den Broek, R., Hoogeveen, H., van den Akker, M., Huisman, B.: A local search algorithm for train unit shunting with service scheduling. Transportation Science (2018, submitted)
van den Broek, R.: Train Shunting and Service Scheduling: an integrated local search approach. Master’s thesis, Utrecht University (2016)
de Oliveira da Costa, P.R., Rhuggenaath, J., Zhang, Y., Akcay, A., Lee, W.J., Kaymak, U.: Data driven policy on feasibility determination for train shunting problem. In: ECML PKDD 2019 (2019)
Dai, L.: A machine learning approach for optimization in railway planning. Master’s thesis, Delft University of Technology, March 2018
Defourny, B., Ernst, D., Wehenkel, L.: Scenario trees and policy selection for multistage stochastic programming using machine learning. J. Comput. (2012)
Hopcroft, J., Karp, R.: An algorithm for maximum matchings in bipartite graphs. Ann. Symp. Switching and Automata Theory 2(4), 225–231 (1973)
Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. CoRR abs/1609.02907 (2016)
Kroon, L.G., Lentink, R.M., Schrijver, A.: Shunting of passenger train units: an integrated approach. Transp. Sci. 42(4), 436–449 (2008)
Lombardi, M., Milano, M.: Boosting combinatorial problem modeling with machine learning. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI-18), pp. 5472–5478 (2018)
Meisel, S., Mattfeld, D.: Synergies of operations research and data mining. Eur. J. Oper. Res. 206(1), 1–10 (2010)
Neumann, M., Garnett, R., Bauckhage, C., Kersting, K.: Propagation kernels: efficient graph kernels from propagated information. Mach. Learn. 102(2), 209–245 (2016)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. CoRR abs/1605.05273 (2016)
Peer, E., Menkovski, V., Zhang, Y., Lee, W.J.: Shunting trains with deep reinforcement learning. In: Proceeding of 2018 IEEE International Conference on Systems, Man, and Cybernetics. IEEE (2018)
Shervashidze, N., Schweitzer, P., van Leeuwen, E., Mehlhorn, K., Borgwardt, K.: Weisfeiler-lehman graph kernels. J. Mach. Learn. Res. 12, 2539–2561 (2011)
van de Ven, A., Zhang, Y., Lee, W.J., Eshuis, H., Wilbik, A.: Determining capacity of shunting yards by combining graph classification with local search. In: Steels, L., Rocha, A., van den Herik, J. (eds.) 11th International Conference on Agents and Artificial Intelligence (ICAART 2019), vol. 2, pp. 285–293. SCITEPRESS-Science and Technology Publications, Lda. (2019)
Verwer, S., Zhang, Y., Ye, Q.C.: Auction optimization using regression trees and linear models as integer programs. Artif. Intell. 244, 368–395 (2017). https://doi.org/10.1016/j.artint.2015.05.004
Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: AAAI, pp. 4438–4445 (2018)
Acknowledgements
The work is partially supported by the NWO funded project Real-time data-driven maintenance logistics (project number: 628.009.012).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
van de Ven, A., Zhang, Y., Lee, WJ. (2019). Boosting Local Search Using Machine Learning: A Study on Improving Local Search by Graph Classification in Determining Capacity of Shunting Yards. In: van den Herik, J., Rocha, A., Steels, L. (eds) Agents and Artificial Intelligence. ICAART 2019. Lecture Notes in Computer Science(), vol 11978. Springer, Cham. https://doi.org/10.1007/978-3-030-37494-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-37494-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37493-8
Online ISBN: 978-3-030-37494-5
eBook Packages: Computer ScienceComputer Science (R0)