Integrating vessel slot allocation and container supply repositioning planning with column-generation algorithm under uncertain demand

The global supply chain has been increasingly disrupted by cargo demand fluctuations, trade policy restrictions, pandemic measures, price competitions, factory order changes, and other factors. The frequent mismatches of the shipment demand against vessel and container supplies render extreme difficulties to ship liners’ smooth cargo delivery due to container supply shortage, booking shortfall, low vessel utilisation, and order fulfilment failure. Based on a previously developed three-echelon collaborative slot allocation planning model which investigated the dynamics among local, regional, and global scales, with containers loading and discharge at multiple vessels and service loops, this paper proceeds to incorporate shipment equipment demand and supply mismatch by considering container supply, empty container repositioning, and demand prospects of the cargo control party. A novel integrated mixedinteger programming framework for slot allocation with comprehensive consideration of the container supply planning and slot exchange under cargo demand uncertainty is developed to optimise container usage, vessel utilisation, and shipment order fulfilment. A recurrent neural
network-based algorithm will be incorporated for container demand prediction of container supply planning, an adaptive slot allocation optimisation for laden and empty containers will be applied, and a column-generation-based algorithm will be used to simplify the ultimate slot allocation optimisation.