Optimizing Berth Allocation in Maritime Transportation with Quay Crane Setup Times Using Reinforcement Learning

Maritime transportation plays a critical role in global trade as it accounts for over 80% of all merchandise movement. Given the growing volume maritime freight, is vital to have an efficient system handling ships and cargos at ports. The current first-come-first-serve method insufficient maintaining operational efficiency, especially under complicated conditions such parallel scheduling with different cargo setups. In addition, face rising demand, data-driven strategies are necessary. To tackle this issue, paper proposes mixed-integer model allocating quay cranes, terminals, berths. It considers not only types, but also time required crane setup. proposed features greedy-insert-based offline algorithm that optimizes berth allocation when vessel information available. situations where uncertain, utilizes online optimization strategy based on reinforcement-learning capable learning from feedback adapting quickly real time. results numerical experiments demonstrate both algorithms can significantly enhance efficiency overall harbor operation. Furthermore, they potential be extended other complex settings.