Management of resource allocation on vehicle-sharing schemes: the case of Thessaloniki's bike-sharing system

The purpose of this paper is to propose a holistic optimization-based framework for addressing the re-balancing problem of vehicle-sharing schemes. In order to address this issue, the problem is decomposed into three (3) sub-problems that include: (1) the dynamic prediction of vehicle demand in stations or zones (in the case of free-floating systems); (2) the optimization of the assignment of vehicles from stations/zones using the predicted demand of the first step; and (3) the optimization of the route that the re-balancing vehicle should follow, under transverse distance minimization objectives, and given the optimized assignment of the second step. As the route optimization of the rebalancing vehicle is computationally intensive, a heuristic algorithm is developed that transforms the route optimization problem into the one (1)-Commodity Pickup and Delivery Capacitated Traveling Salesman Problem. The applicability of the proposed methodology is illustrated through its application on the real case of the bike-sharing system in the city of Thessaloniki in Greece.