DOI QR코드

DOI QR Code

Practical method to improve usage efficiency of bike-sharing systems

  • Lee, Chun-Hee (Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research) ;
  • Lee, Jeong-Woo (Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research) ;
  • Jung, YungJoon (Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research)
  • Received : 2021.10.28
  • Accepted : 2022.02.20
  • Published : 2022.04.10

Abstract

Bicycle- or bike-sharing systems (BSSs) have received increasing attention as a secondary transportation mode due to their advantages, for example, accessibility, prevention of air pollution, and health promotion. However, in BSSs, due to bias in bike demands, the bike rebalancing problem should be solved. Various methods have been proposed to solve this problem; however, it is difficult to apply such methods to small cities because bike demand is sparse, and there are many practical issues to solve. Thus, we propose a demand prediction model using multiple classifiers, time grouping, categorization, weather analysis, and station correlation information. In addition, we analyze real-world relocation data by relocation managers and propose a relocation algorithm based on the analytical results to solve the bike rebalancing problem. The proposed system is compared experimentally with the results obtained by the real relocation managers.

Keywords

Acknowledgement

This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2018-0-00225, Development of City Interior Digital Twin Technology to establish Scientific Policy).

References

  1. K. H. Law and J. P. Lynch, Smart city: Technologies and challenges, IT Prof. 21 (2019), no. 6, 46-51. https://doi.org/10.1109/mitp.2019.2935405
  2. L. Caggiani, R. Camporeale, M. Ottomanelli, and W. Y. Szeto, A modeling framework for the dynamic management of freefloating bike-sharing systems, Transp. Res. Part C: Emerg. Technol. 87 (2018), 159-182. https://doi.org/10.1016/j.trc.2018.01.001
  3. Y. Cheng, J. Wang, and Y. Wang, A user-based bike rebalancing strategy for free-floating bike sharing systems: A bidding model, Transp. Res. Part E 154 (2021), 102438. https://doi.org/10.1016/j.tre.2021.102438
  4. F. Chiariotti, C. Pielli, A. Zanella, and M. Zorzi, A dynamic approach to rebalancing bike-sharing systems, Sensors 18 (2018), no. 2, 512. https://doi.org/10.3390/s18020512
  5. M. Dell Amico, M. Iori, S. Novellani, and A. Subramanian, The bike sharing rebalancing problem with stochastic demands, Trans. Res. Part B 118 (2018), 362-380. https://doi.org/10.1016/j.trb.2018.10.015
  6. P. Leclaire and F. Couffin, Method for static rebalancing of a bike sharing system, IFAC-PapersOnLine 51 (2018), no. 11, 1561-1566. https://doi.org/10.1016/j.ifacol.2018.08.274
  7. B. Legros, Dynamic repositioning strategy in a bike-sharing system; how to prioritize and how to rebalance a bike station, Eur. J. Oper. Res. 272 (2019), 740-753. https://doi.org/10.1016/j.ejor.2018.06.051
  8. K. B. Svenja Reiss, A relocation strategy for munich's bike sharing system: Combining an operator-based and a user-based scheme, Transp. Res. Procedia 22 (2017), 105-114. https://doi.org/10.1016/j.trpro.2017.03.016
  9. Z. Tian, J. Zhou, W. Y. Szeto, and L. Tian, The rebalancing of bike-sharing system under flow-type task window, Transp. Res. Part C: Emerg. Technol. 112 (2020), 1-27. https://doi.org/10.1016/j.trc.2020.01.015
  10. L. Caggiani, R. Camporeale, Z. Hamidi, and C. Zhao, Evaluating the efficiency of bike-sharing stations with data envelopment analysis, Sustainability 13 (2021), no. 2.
  11. Y. Feng, R. C. Affonso, and M. Zolghadri, Analysis of bike sharing system by clustering: the velib' case, IFAC-PapersOnLine 50 (2017), no. 1, 12422-12427. https://doi.org/10.1016/j.ifacol.2017.08.2430
  12. D. Li, Y. Zhao, and Y. Li, Time-series representation and clustering approaches for sharing bike usage mining, IEEE Access 7 (2019), 177856-177863. https://doi.org/10.1109/access.2019.2958378
  13. Y. Yao, Y. Zhang, L. Tian, N. Zhou, Z. Li, and M. Wang, Analysis of network structure of urban bike-sharing system: A case study based on real-time data of a public bicycle system, Sustainability 11 (2019), no. 19, 5425. https://doi.org/10.3390/su11195425
  14. X. Zhou, Understanding spatiotemporal patterns of biking behavior by analyzing massive bike sharing data in chicago, PLOS ONE 10 (2015), e0137922. https://doi.org/10.1371/journal.pone.0137922
  15. https://en.wikipedia.org/wiki/Data_envelopment_analysis
  16. G. Cantelmo, R. Kucharski, and C. Antoniou, Low-dimensional model for bike-sharing demand forecasting that explicitly accounts for weather data, Transp. Res. Record 2674 (2020), no. 8, 132-144. https://doi.org/10.1177/0361198120932160
  17. P. Hulot, D. Aloise, and S. D. Jena, Towards station-level demand prediction for effective rebalancing in bike-sharing systems, (ACM SIGKDD international conference on knowledge discovery & data mining KDD, London, UK), Aug. 2018, pp. 378-386.
  18. X. Liu and K. Pelechrinis, Excess demand prediction for bike sharing systems, PLOS ONE 16 (2021), e0252894. https://doi.org/10.1371/journal.pone.0252894
  19. Y. Pan, R. C. Zheng, J. Zhang, and X. Yao, Predicting bike sharing demand using recurrent neural networks, Procedia Comput. Sci. 147 (2018), 562-566.
  20. A. A. Ramesh, S. P. Nagisetti, N. Sridhar, K. Avery, and D. Bein, Station-level demand prediction for bike-sharing system, (IEEE 11th Annual Computing and Communication Workshop and Conference, Las Vegas, NV, USA), Jan. 2021, pp. 916-921.
  21. C. Sardinha, A. C. Finamore, and R. Henriques, Context-aware demand prediction in bike sharing systems: incorporating spatial, meteorological and calendrical context, 2021. https://arxiv. org/abs/2105.01125
  22. D. Singhvi, S. Singhvi, P. I. Frazier, S. G. Henderson, E. O'Mahony, D. B. Shmoys, and D. B. Woodard, Predicting bike usage for new york city's bike sharing system (Computational Sustainability, Papers from the 2015 AAAI Workshop, Austin, Texas, USA), Jan. 2015.
  23. D. Singhvi, S. Singhvi, P. I. Frazier, S. G. Henderson, E. O'Mahony, D. B. Shmoys and D. B. Woodard, Predicting bike usage for new york city's bike sharing system (Computational Sustainability, Papers from the 2015 AAAI Workshop, Austin, Texas, USA), Jan. 2015.
  24. S. Ve and Y. Cho, A rule-based model for seoul bike sharing demand prediction using weather data, Eur. J. Remote Sensing 53 (2020), no. S1, 166-183. https://doi.org/10.1080/22797254.2020.1725789
  25. N. Gast, G. Massonnet, D. Reijsbergen, and M. Tribastone, Probabilistic forecasts of bike-sharing systems for journey planning (CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne Australia), Oct. 2015, pp. 703-712.
  26. S. Ghosh, P. Varakantham, Y. Adulyasak, and P. Jaillet, Dynamic repositioning to reduce lost demand in bike sharing systems, J. Artif. Intell. Res. 58 (2017), 387-430. https://doi.org/10.1613/jair.5308
  27. C.-H. Lee, J.-W. Lee, Y.-J. Jung and I.-Y. Ch, Relocation framework to improve the usage efficiency of bicycle-sharing systems (23rd International Conference on Advanced Communication Technology, Pyeong Chang, Rep. of Korea), Feb. 2021. https:// doi.org/10.23919/ICACT51234.2021.9370711
  28. https://scikit-learn.org/stable/auto_examples/model_ selection/plot_roc.html
  29. https://scikit-learn.org/stable/modules/generated/sklearn. multiclass.OneVsRestClassifier.html