Data-Driven Robust Integrated Car-Sharing Scheduling with Heterogeneous Vehicles Considering Uncertain Dispatcher and Relocation Times

Car-sharing systems, as an important form of shared transport, face spatial asymmetry between vehicle availability and customer demand across stations, leading to supply–demand imbalance and complex scheduling challenges. Heterogeneous vehicles can better meet diverse customer demands by offering vehicles with different capacities. Meanwhile, uncertainty in dispatcher movement time and vehicle relocation time may affect the reliability of scheduling plans. To address these issues, this paper focuses on a one-way station-based car-sharing problem, considering integrated scheduling, heterogeneous vehicles, uncertain dispatcher movement time and vehicle relocation time simultaneously. We use a data-driven approach to construct separate uncertainty sets for vehicle relocation time and dispatcher movement time from historical Taxi & Limousine Commission (TLC) records and Citi Bike electric-bike records, respectively. A robust optimization model is then developed to improve order fulfillment and scheduling stability. We develop a hybrid approach that combines adaptive large neighborhood search and a genetic algorithm (ALNS/GA), and incorporates robustness into solution decoding and fitness evaluation under the data-driven uncertainty sets. Numerical experiments based on real-world TLC and Citi Bike data are conducted to evaluate ALNS/GA, integrated scheduling, and different uncertainty-budget parameters. The results show that integrated scheduling reduces average generalized costs, while robust scheduling improves out-of-sample reliability with a modest increase in cost. Sensitivity analysis also offers useful managerial insights.