Combined Stochastic and Robust Optimization for Electric Autonomous Mobility-on-Demand with Nested Benders Decomposition
The research developed a combined stochastic and robust model predictive control framework for Electric Autonomous Mobility-on-Demand (EAMoD) fleets. It uses Bayesian neural network forecasts to predict travel demand and charger availability, then solves a large mixed-integer linear program using a tailored Nested Benders Decomposition to optimize dispatch, rebalancing, and charging decisions under uncertainty. Results show significant improvements in passenger waiting times, reduced rebalancing distance, and lower electricity costs compared to existing methods.