An adaptive large neighborhood search heuristic for the multi-port continuous berth allocation problem
This addresses operational cost optimization for carriers and terminal operators in maritime logistics, but it is incremental as it applies an existing heuristic method to a new problem variant.
The paper tackles the multi-port continuous berth allocation problem (MCBAP), which integrates vessel scheduling and berth allocation across multiple ports, by developing an adaptive large neighborhood search (ALNS) algorithm enhanced with local search, achieving high-quality solutions in short computational times for larger instances.
In this paper, we study a problem that integrates the vessel scheduling problem with the berth allocation into a collaborative problem denoted as the multi-port continuous berth allocation problem (MCBAP). This problem optimizes the berth allocation of a set of ships simultaneously in multiple ports while also considering the sailing speed of ships between ports. Due to the highly combinatorial character of the problem, exact methods struggle to scale to large-size instances, which points to exploring heuristic methods. We present a mixed-integer problem formulation for the MCBAP and introduce an adaptive large neighborhood search (ALNS) algorithm enhanced with a local search procedure to solve it. The computational results highlight the method's suitability for larger instances by providing high-quality solutions in short computational times. Practical insights indicate that the carriers' and terminal operators' operational costs are impacted in different ways by fuel prices, external ships at port, and the modeling of a continuous quay.