An optimization study on dynamic berth allocation based on vessel arrival time prediction

Abstract

Berth allocation is a critical aspect of port operations, and its efficiency directly affects the overall performance of port operations. However, in practice, the significant uncertainty and complexity of container vessel arrival times pose challenges to the formulation of berth allocation plans. To address this issue, this study leverages historical data from the Automatic Identification System (AIS) and employs various machine learning models to accurately predict container vessel arrival times. The prediction results are then integrated into berth allocation optimization. The berth allocation model takes into account factors such as tidal conditions and berthing positions to design an optimal berth allocation strategy, which is solved using a genetic algorithm. A comparative analysis of case studies demonstrates the optimization effectiveness of the proposed model. Compared with the actual operational plan of the port, vessel waiting time is reduced by 28 %, significantly improving the service quality and operational efficiency of port operations.