253 / 2024-04-23 21:07:35

Hybrid fleet management and vehicle repositioning in mobility-as-a-service operations

Mobility-as-a-service,Crowd-sourced vehicles,Distributionally robust optimization

While Mobility-as-a-Service (MaaS) platforms have revolutionized urban transportation and fundamentally transformed travelers' experience and engagement, they encounter a significant challenge in maintaining a spatial balance between supply and demand, particularly with the inclusion of crowd-sourced freelance drivers. In this study, we propose a hybrid supply-side management strategy that integrates the physical repositioning of in-house vehicles with the utilization of crowd-sourced freelance vehicles through spatial pricing. We employ a Multinomial Logit model to characterize the repositioning behavior of crowd-sourced drivers, enabling us to consider a lower-level equilibrium problem embedded in a bilevel program. A tailored ambiguity set using the Wasserstein metric within the framework of distributionally robust optimization (DRO) is constructed to characterize demand uncertainty, while a linear decision rule (LDR) approximation facilitates a tractable reformulation without any loss of optimality. We validate the practical applicability of our model using a dataset from RideAustin, a ride-hailing platform operating in Austin, Texas. We find that the hybrid fleet approach gets the best of both worlds by reducing operational costs using crowd-sourced vehicles and enhancing system robustness using in-house vehicles. Interestingly, we show that a ``sweet-spot" may exist as an optimal ratio between the number of in-house and crowd-sourced vehicles that minimizes the overall operational cost.