Bike-Sharing Fleet Allocation Optimization Based on Demand Gap and Cycle Rebalancing Strategies

In Bike-Sharing System (BSS), the initial number of bikes at station will affect the time interval and the amount of rebalancing, which is usually empirically determined and does not reflect the characteristics of consumer demand in finer time granularity, thus possibly leading to biased conclusions. In this paper, a fleet allocation method considering demand gap is first proposed to calculate the initial number of bikes at each station. Then, taking the number of demand gap periods as the decision variable, an optimization model is built to minimize the total rebalancing amount. Furthermore, the research periods are divided into multiple subcycles, the single-cycle and multicycle rebalancing strategies are presented, and the additional subcycle rebalancing method is introduced to amend the number of bikes between subcycles to decrease the rebalancing amount of the next subcycle. Finally, our methods are verified in effectively decreasing the rebalancing amount in a long-term rebalancing problem.

A crowdsourced dynamic repositioning strategy for public bike sharing systems

<p style='text-indent:20px;'>Public bike sharing systems have become the most popular shared economy application in transportation. The convenience of this system depends on the availability of bikes and empty racks. One of the major challenges in operating a bike sharing system is the repositioning of bikes between rental sites to maintain sufficient bike inventory in each station at all times. Most systems hire trucks to conduct dynamic repositioning of bikes among rental sites. We have analyzed a commonly used repositioning scheme and have demonstrated its ineffectiveness. To realize a higher quality of service, we proposed a crowdsourced dynamic repositioning strategy: first, we analyzed the historical rental data via the random forest algorithm and identified important factors for demand forecasting. Second, considering 30-minute periods, we calculated the optimal bike inventory via integer programming for each rental site in each time period with a sufficient crowd for repositioning bikes. Then, we proposed a minimum cost network flow model in a time-space network for calculating the optimal voluntary rider flows for each period based on the current bike inventory, which is adjusted according to the forecasted demands. The results of computational experiments on real-world data demonstrate that our crowdsourced repositioning strategy may reduce unmet rental demands by more than 30% during rush hours compared to conventional trucks.</p>

Using Machine Learning Methods to Predict Demand for Bike Sharing

We applied four machine learning models, linear regression, the k-nearest neighbors (KNN), random forest, and support vector machine, to predict consumer demand for bike sharing in Seoul. We aimed to advance previous research on bike sharing demand by incorporating features other than weather - such as air pollution, traffic information, Covid-19 cases, and social economic factors- to increase prediction accuracy. The data were retrieved from Seoul Public Data Park website, which records the counts of public bike rentals in Seoul of Korea from January 1 to December 31, 2020. We found that the two best models are the random forest and the support vector machine models. Among the 29 features in six categories the features in the weather, pollution, and Covid-19 outbreak categories are the most important in model prediction. While almost all social economic features are the least important, we found that they help enhance the performance of the models.