Deep Learning for Short-Term Prediction of Available Bikes on Bike-Sharing Stations

Enrico Collini,Paolo Nesi,Gianni Pantaleo

doi:10.1109/access.2021.3110794

Enrico Collini, Paolo Nesi + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3110794

Copy DOI

Abstract

Bike-sharing is adopted as a valid option replacing traditional public transports since they are eco-friendly, prevent traffic congestions, reduce any possible risk of social contacts which happen mostly on public means. However, some problems may occur such as the irregular distribution of bikes on related stations/racks/areas, and the difficulty of knowing in advance what the rack status will be like, or predicting if there will be bikes available in a specific bike-station at a certain time of the day, or if there will be a free slot to leave the rented bike. Thus, providing predictions can be useful to improve the service quality, especially in those cases where bike racks are used for e-bikes, which need to be recharged. This paper compares the state-of-the-art techniques to predict the number of available bikes and free bike-slots in bike-sharing stations (i.e., bike racks). To this end, a set of features and predictive models were compared to identify the best models and predictors for short-term predictions, namely of 15, 30, 45, and 60 minutes. The study has demonstrated that deep learning and in particular Bidirectional Long Short-Term Memory networks (Bi-LSTM) offers a robust approach for the implementation of reliable and fast predictions of available bikes, even with a limited amount of historical data. This paper has also reported an analysis of feature relevance based on SHAP that demonstrated the validity of the model for different cluster behaviours. Both solution and its validation were derived by using data collected in bike-stations in the cities of Siena and Pisa (Italy), in the context of Sii-Mobility National Research Project on Mobility and Transport and Snap4City Smart City IoT infrastructure.

Highlights

The cities are becoming large and complex entities.Today, about 55% of the world’s population lives in urban areas, and the figure is expected to reach the 68% in 2050, according to the "World Urbanization Prospects 2018", published by the United Nations Department of Economics and Social Affairs [1]
The alternative could be floating bike-sharing in which the bikes are more intelligent, being capable to communicate with the central management servers their position, such as the Mobike solution
The minimum MAPE was registered for Cluster 1 for the prediction targets by the Bidirectional Long Short-Term Memory networks (Bi-Long Short-Term Memory networks (LSTM))

Summary

INTRODUCTION

The cities are becoming large and complex entities. Today, about 55% of the world’s population lives in urban areas, and the figure is expected to reach the 68% in 2050, according to the "World Urbanization Prospects 2018", published by the United Nations Department of Economics and Social Affairs [1]. A. ARTICLE CONTRIBUTIONS AND STRUCTURE The main contribution of this paper consists in presenting a solution comparing the state-of-the-art technologies for short-term prediction (15, 30, 45, and 60 minutes) of the available bikes on bike-sharing stations, and of the number of free slots by knowing the size of the station and the number of broken bikes, for the cities of Siena and Pisa in Italy, considering a limited data history of 3 months. Prediction of available bikes is a non-linear process whose dynamic changes involve multiple kinds of factors, coming from the context To this end, the solution has been obtained by taking into account different cities and locations, and despite the changes in Siena and Pisa, the same model has been used and the same features have been identified in both cases, demonstrating the validity of the derived results.

RELATED WORKS

PREDICTION MODELS

Results obtained for Results obtained for

CONCLUSIONS