Applied Intelligence

, Volume 49, Issue 5, pp 1968–1981 | Cite as

Dynamic bicycle scheduling problem based on short-term demand prediction

  • Haitao XuEmail author
  • Feng Duan
  • Pan Pu


As a low-cost environmentally-friendly travel mode, public bicycles have been widely applied in many large cities and have greatly facilitated people’s daily lives. However, it is hard to find bicycles to rent or places to return at some stations in peak hours due to the unbalanced distribution of public bicycles. And the traditional scheduling methods have hysteresis, in general, the demands might have changed when the dispatch vehicle arrives the station. To better solve such problems, we propose a dynamic scheduling (DBS) model based on short-term demand prediction. In this paper, we first adopt K-means to cluster the stations and adopt random forest (RF) to predict the check-out number of bikes in each clustering. In addition, the multi-similarity inference model is applied to calculate the check-out probability of each station for check-out prediction, and a probabilistic model is proposed for check-in prediction in the cluster. Based on the prediction results, an enhanced genetic algorithm (E-GA) is applied to optimize the bicycle scheduling route. Finally, we evaluated the performance of the models through a one-year dataset from Chicago’s public bike-sharing system (BSS) with more than 500 stations and over 3.8 million travel records. Compared with other prediction methods and scheduling approaches, the proposed approach has better performance.


Dynamic bicycle scheduling problem K-means Random forest Multi-similarity inference Genetic algorithm 



This work was financially supported by Chinese National Science Foundation (61572165) and Projects of Zhejiang Province (LGF18F030006).


  1. 1.
    Abdallah AMFM, Essam DL, Sarker RA (2017) On solving periodic re-optimization dynamic vehicle routing problems. Appl Soft Comput 55:1–12. CrossRefGoogle Scholar
  2. 2.
    Álvaro L, Paz JD, González GV, Iglesia D, Bajo J (2018) Multi-agent system for demand prediction and trip visualization in bike sharing systems. Appl Sci 8(1):67. CrossRefGoogle Scholar
  3. 3.
    Breiman L (2001) Random forest. Mach Learn 45:5–32CrossRefzbMATHGoogle Scholar
  4. 4.
    Chen LB, Zhang DQ, Wang L, Yang DQ, Ma XJ, et al (2016) Dynamic cluster-based over-demand prediction in bike sharing systems. ACM, pp 841–852.
  5. 5.
    Chen PC, Hsieh HY, Sigalingging XK, Chen YR, Leu JS (2017) Prediction of station level demand in a bike sharing system using recurrent neural networks. In: IEEE Vehicular Technology Conference, pp 1–5Google Scholar
  6. 6.
    Costa PRDOD, Mauceri S, Carroll P, Pallonetto F (2018) A genetic algorithm for a green vehicle routing problem. Electron Notes Discrete Math 64:65–74. MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Dong HZ, Zhao JY, Guo HF, Guo MF (2009) Research on the dynamic model and rolling horizon scheduling algorithm for public-use bicycle vehicle scheduling problem. Highw Eng 34(6):68–71Google Scholar
  8. 8.
    Feng YL, Wang SS (2017) A forecast for bicycle rental demand based on random forests and multiple linear regression. IEEE.
  9. 9.
    Hanshar FT, Ombuki-Berman BM (2007) Dynamic vehicle routing using genetic algorithms. Kluwer Academic Publishers 27:89–99. zbMATHGoogle Scholar
  10. 10.
    He L, Li XD, Chen DW, Lu J, Wu YY (2013) Research on the demand forecast model of public bike dynamic scheduling system. Journal of Wuhan University of Technology 37(2):278–282. Google Scholar
  11. 11.
    He Y, Han Y (2017) Research on public bicycle dispatching path based on ant colony algorithm. Agricultural Equipment & Vehicle Engineering 55(1):27–30. Google Scholar
  12. 12.
    Li Y, Szeto WY, Long J, Shui CS (2016) A multiple type bike repositioning problem. TRANSPORT RES B-METH 90:263–278. CrossRefGoogle Scholar
  13. 13.
    Li YX, Zheng Y, Zhang HC, Chen L (2015) Traffic prediction in a bike-sharing system. ACM 33:1–10. Google Scholar
  14. 14.
    Lin L, He ZB, Peeta S, Wen XJ (2017) Predicting Station-level Hourly Demands in a Large-scale Bike-sharing Network: A Graph Convolutional Neural Network ApproachGoogle Scholar
  15. 15.
    Mao YM, Shi SY, Yang H, Zhang YY (2012) Research on method of double-layers BP neural network in bicycle flow prediction. Springer, pp 86–88.
  16. 16.
    Mohammed MA, Gani MKA, Hamed RI, Mostafa SA, Ahmad MS, Ibrahim DA (2017) Solving vehicle routing problem by using improved genetic algorithm for optimal solution. Journal of Computational Science 21:255–262. CrossRefGoogle Scholar
  17. 17.
    Montemanni R, Gambardella LM, Rizzoli AE, Donati AV (2005) Ant colony system for a dynamic vehicle routing problem. J Comb Optim 10(4):327–343. MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    O’Mahony E, Shmoys DB (2015) Data analysis and optimization for (citi)bike sharing. AAAI Press, Palo Alto, pp 687–694. Google Scholar
  19. 19.
    Schuijbroek J, Hampshire RC, Hoeve WJV (2017) Inventory rebalancing and vehicle routing in bike sharing systems. EUR J OPER RES 257 (3):992–1004. MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Sörensen K, Vergeylen N (2015) The bike request scheduling problem. Springer International Publishing, Berlin, pp 294–301Google Scholar
  21. 21.
    Tian YJ, Xie QH (2016) Dynamic scheduling of public bicycles based on artificial bee colony algorithm. In: Qi E, Shen J, Dou R (eds) Proceedings of the 23rd international conference on industrial engineering and engineering management 2016. Atlantis Press, Paris, pp 245–249.
  22. 22.
    Tran TD, Ovtracht N, D’Arcier BF (2015) Modeling bike sharing system using built environment factors. Procedia Cirp 30:293–298. CrossRefGoogle Scholar
  23. 23.
    Wang KZ, Lan SL, Zhao YX (2017) A genetic-algorithm-based approach to the two-echelon capacitated vehicle routing problem with stochastic demands in logistics service. J Oper Res Soc, pp 1–13.
  24. 24.
    Xie XP, Qiu JD, Tang MA, Tamp M (2017) Demand prediction of public bicycle rental station based on Elman neural network. Comput Eng Appl 53(16):221–224. Google Scholar
  25. 25.
    Xu HT, Duan F, Pu P (2018) Solving dynamic vehicle routing problem using enhanced genetic algorithm with penalty factors. IJPE 14(4):611–620. Google Scholar
  26. 26.
    Xu HT, Ying J, Wu H, Lin F (2013) Public bicycle traffic flow prediction based on a hybrid model. Appl Math Inf Sci 7(2):667–674. CrossRefGoogle Scholar
  27. 27.
    Yang JW, Zhou ZP, Cai YF (2016) Public bicycle dynamic scheduling model based on improved ant colony algorithm. Transactions of Beijing Institute of Technology 36(2):121–124Google Scholar
  28. 28.
    Yang ZD, Hu J, Shu YC, Cheng P, Chen JM, Moscibroda T (2016) Mobility modeling and prediction in Bike-Sharing system. ACM, pp 165–178.
  29. 29.
    Zhang JW, Pan X, Li MY, Yu PS (2016) Bicycle-Sharing System analysis and trip prediction. In: IEEE international conference on mobile data management, pp 174–179.
  30. 30.
    Zeng XY, Yang YX, Chen S, Peng YL (2017) Traffic flow trend forecast of public bicycle network based on ARIMA model. CECE 2017, pp 334–338Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyHangzhou Dianzi UniversityHangzhouChina

Personalised recommendations