A hybrid e-bike sharing system design problem considering multiple types of facilities

Abstract

Shared electric bikes (e-bikes) have become a rapidly growing mode of transportation worldwide, with electric bike-sharing systems (EBSSs) successfully implemented in numerous cities. The mainstream EBSSs can generally be categorized into two types: station-based and free-floating (or dockless). Each type has its respective advantages and disadvantages. For example, free-floating systems have a lower total construction and maintenance cost, but some users return e-bikes at improper locations without considering social impacts, such as blocking vehicle and pedestrian movements, and the induced safety issues. A hybrid e-bike sharing system (HEBSS) that combines elements from both systems has the potential to exploit the advantages of both and overcome their drawbacks, leading to an improvement in system performance. However, few existing studies have proposed a methodology to design such a system to demonstrate its effectiveness and address the inconsiderate e-bike return behavior.

In this paper, we formulate the design problem of an HEBSS as a bi-level optimization problem. The upper-level problem is to determine the locations and capacities of various facilities, including charging stations and geofencing areas, aiming to maximize social welfare under a budget constraint. The lower-level problem is an e-bike sharing network equilibrium problem with elastic demand considering the inconsiderate drop-off behavior of users, waiting time costs, roaming behavior during rental and return processes, and parking rewards and fines. The upper-level problem is solved by our proposed hybrid solution method, which is based on genetic algorithm coupled with our proposed capacity-setting heuristic. The lower-level problem is transformed into a fixed demand equivalent problem and solved by the self-regulated averaging method. We present numerical results to demonstrate the properties of the problem, identify the key factors that affect the design, illustrate the performance of the proposed hybrid solution algorithm, and provide design insights to the system operator.