Abstract
Order-dispatching strategy is fundamental for online ride-hailing systems in three major ways. First, it should be capable of effectively matching hundreds of orders to thousands of vehicles in less than 1 min, whereas both orders and vehicles are geographically widely distributed. Second, it should decide how to fairly allocate profit among participators. Third, it should unify interests of present and future. Conflicts always exist within the three objectives. We observe that the system is dynamically balanced during fine-tuned time intervals. Based on this observation, we propose a novel dispatching strategy capable of juggling the three objectives. By applying optimal transport theory, we demonstrate that, under appropriate presumptions, this dispatching strategy is ruled by the optimal transport plan realizing the Wasserstein distance between distributions of orders and vehicles. Furthermore, we develop a kit of methodological and algorithmic tools which has substantial and sensible advantages in characterizing and optimizing the system.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Transportation Research Record: Journal of the Transportation Research Board
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.