Demand Prediction and Optimal Allocation of Shared Bikes Around Urban Rail Transit Stations

Abstract

The imbalance between the supply and demand of shared bikes is prominent in many urban rail transit stations, which urgently requires an efficient vehicle deployment strategy. In this paper, we propose an integrated model to optimize the deployment of shared bikes around urban rail transit stations, incorporating a seasonal autoregressive integrated moving average with long short-term memory (SARIMA-LSTM) hybrid model that is used to predict the heterogeneous demand for shared bikes in space and time. The shared bike deployment strategy was formulated based on the actual deployment process and under the principle of cost minimization involving labor and transportation. The model is applied using the big data of shared bikes in Xicheng District, Beijing. Results show that the SARIMA-LSTM hybrid model has great advantages in predicting the demand for shared bikes. The proposed allocation strategy provides a new way to solve the imbalance challenge between the supply and demand of shared bikes and contributes to the development of a sustainable transportation system.

Keywords

Bike sharing / Demand prediction / Bike-sharing deployment / Hybrid model / Big data

References

[1] Lu K, Han B, Zhou X. Smart urban transit systems: from integrated framework to interdisciplinary perspective. Urban Rail Transit, 2018, 4(2): 49-67

[2] Bai Y, Liu X, Huang Y, Wan X. The influence of shared bicycle on urban rail transit operation and management in Beijing. Urban Rapid Rail Transit, 2018, 31(03): 119-124.

[3] Zuo T, Wei H, Chen N, Zhang C. First-and-last mile solution via bicycling to improving transit accessibility and advancing transportation equity. Cities, 2020, 99: 102614

[4] Cheng L, Mi ZF, Coffman D, Meng J, Liu DN, Chang DF. The role of bike sharing in promoting transport resilience. Netw Spat Econ, 2021

[5] Zhang F, Liu W. An economic analysis of integrating bike sharing service with metro systems. Transp Res Part D Transp Environ, 2021, 99: 103008

[6] Hu B, Gao Y, Yan J, Sun Y, Ding Y, Bian J, Dong X, Sun H. Understanding the operational efficiency of bicycle-sharing based on the influencing factor analyses: a case study in Nanjing China. J Adv Transp, 2021, 2021: 1-14

[7] Molinillo S, Ruiz-Montañez M, Liébana-Cabanillas F. User characteristics influencing use of a bicycle-sharing system integrated into an intermodal transport network in Spain. Int J Sustain Transp, 2020, 14(7): 513-524

[8] Lin P, Weng J, Hu S, Alivanistos D, Li X, Yin B. Revealing spatio-temporal patterns and influencing factors of dockless bike sharing demand. IEEE Access, 2020, 8: 66139-66149

[9] Zeng P, Wei M, Liu X. Investigating the spatiotemporal dynamics of urban vitality using bicycle-sharing data. Sustainability, 2020, 12(5): 1714

[10] Xu M, Liu H, Yang H. A deep learning based multi-block hybrid model for bike-sharing supply-demand prediction. IEEE Access, 2020, 8: 85826-85838

[11] Xu T, Han G, Qi X, Du J, Lin C, Shu L. A hybrid machine learning model for demand prediction of edge-computing-based bike-sharing system using internet of things. IEEE Internet Things J, 2020, 7(8): 7345-7356

[12] Chen J, Li K, Li K, Yu PS, Zeng Z (2021) Dynamic Bicycle Dispatching of Dockless Public Bicycle-sharing Systems using Multi-objective Reinforcement Learning, arXiv preprint arXiv:2101.07437

[13] Ma T, Chao L, Erdogan S. Bicycle sharing and public transit: does capital bikeshare affect metrorail ridership in Washington, D.C.?. Urban Rapid Rail Transit, 2015, 2534(1): 1-9.

[14] Borgnat P, Abry P, Flandrin P, Robardet C, Rouquier J, Fleury E. Shared bicycles in a city: a signal processing and data analysis perspective. Adv Complex Syst, 2011, 14(3): 415-438

[15] Chen L, Zhang D, Wang L, Yang D, Ma X, Li S, Wu Z, Pan G, Thi-Mai-Trang N, Jakubowicz J (2016) Dynamic Cluster-Based Over-Demand Prediction in Bike Sharing Systems. In: UBICOMP'16: Proceedings of the 2016 ACM international joint conference on pervasive and ubiquitous computing (2016) 841-852. https://doi.org/10.1145/2971648.2971652.

[16] Feng S, Hao C, Du C, Li J, Ning J (2018) A Hierarchical Demand Prediction Method with Station Clustering for Bike Sharing System. In: 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), 2018

[17] Lin L, He Z, Peeta S. Predicting station-level hourly demand in a large-scale bike sharing network: a graph convolutional neural network approach. Transp Res Part C Emerging Technol, 2018, 97: 258-276

[18] Wang B, Kim I. Bicycle sharing and public transit: does capital bikeshare affect metrorail ridership in Washington, D.C.?. Transp Res Procedia, 2018, 34: 171-178

[19] Sohrabi S, Ermagun A. Dynamic bike sharing traffic prediction using spatiotemporal pattern detection. Transp Res Part D Transp Environ, 2021, 90: 102647

[20] Wu X, Lyu C, Wang Z, Liu Z. Station-level hourly bike demand prediction for dynamic repositioning in bike sharing systems, 2019, Berlin: Springer 19-27.

[21] Kaltenbrunner A, Meza R, Grivolla J, Codina J, Banchs R. Urban cycles and mobility patterns: exploring and predicting trends in a bicycle-based public transport system. Pervasive Mob Comput, 2010, 6(4): 455-466

[22] Yoon JW, Pinelli F, Calabrese F (2012) Cityride: A Predictive Bike Sharing Journey Advisor. In: IEEE International Conference on Mobile Data Management, 2012, pp. 306-311.

[23] Liu J, Qiao L, Meng Q, Chen W, Fu Y (2016) Station Site Optimization in Bike Sharing Systems. In: 2015 IEEE International Conference on Data Mining (ICDM), 2016

[24] Mehdizadeh Dastjerdi A, Morency C. Dynamic bike sharing traffic prediction using spatiotemporal pattern detection. Sensors, 2022, 22(3): 1060

[25] Boonjubut K, Hasegawa H. Multivariate time series analysis using recurrent neural network to predict bike-sharing demand, 2020, Singapore: Springer 69-77.

[26] Ma X, Yin Y, Jin Y, He M, Zhu M. Short-term prediction of bike-sharing demand using multi-source data: a spatial-temporal graph attentional LSTM approach. Appl Sci Basel, 2022, 12(3): 1061

[27] Forma IA, Raviv T, Tzur M. A 3-step math heuristic for the static repositioning problem in bike-sharing systems. Transp Res Part B Methodolog, 2015, 71: 230-247

[28] Angeloudis P, Hu J, Bell MGH. A strategic repositioning algorithm for bicycle-sharing schemes. Transp A Transp Sci, 2014, 10(8): 759-774

[29] Jost JD, Herr T, Lecaplain C, Brasch V, Pfeiffer M, Kippenberg TJ. Counting the cycles of light using a self-referenced optical microresonator. Optica, 2014, 2(8): 706

[30] Jiménez E, Soriguera F. A new dynamic repositioning approach for bike sharing systems. Transp Res Procedia, 2020, 47: 227-234

[31] Raviv T, Tzur M, Forma IA. Static repositioning in a bike-sharing system: models and solution approaches. EURO J Transp Logist, 2013, 2(3): 187-229

[32] Feng T, Arentze TA, Timmermans HJ. Assessing the relative importance of input variables for route choice modeling: a neural network approach. J East Asia Soc Transp Stud, 2011, 9: 341-353

[33] Wang Z, Cheng L, Li Y, Li Z. Spatiotemporal characteristics of bike-sharing usage around rail transit stations: evidence from Beijing, China. Sustainability, 2020, 12(4): 1299

Funding

Beijing Municipal Natural Science Foundation(No. 9202012)