A Framework for Adaptive Ride-Sharing and Management of Electric Vehicles

This project presents the design, implementation and evaluation of a carbon-neutral, community-based, scalable ride-sharing service. Its models formalise the partition of an AEVs fleet over the SECs of a city, as well as the allocation of trip petitions (TPs) to AEVs, their routing and charging scheduling over a simulated time horizon. These models integrate energy generation, allocation and re-routing constraints to maximise the number of TPs served. The solution approach to implement the models includes the application of Greedy-based Heuristics and Metaheuristics, Reinforcement Learning and Mixed Integer Programming techniques. Research Questions

• The formulation of a Carbon-Neutral, Community-Based, Reactive and Scalable Ride-Sharing Service presented as a variant of the classical Dynamic Vehicle Routing Problem with Time Windows aligning with the ambition of the aforementioned EU Green Deal goals.

• This research objective extends Research Objective 1 by integrating the design, implementation and evaluation of the vehicle fleet allocation to the ride-sharing service.

• This research objective extends Research Objective 1 by integrating the design, implementation and evaluation of reward-based charging scheduling to the ride-sharing service.