Abstract
Loading operations are a crucial part of container terminal activities and play a key role in influencing shoreline operation efficiency. To overcome the challenge of mismatched local ship decisions and global yard decisions during single-vessel operations, which often result in conflicts related to container retrieval in the yard, a novel intelligent decision-making model for stack-yard positioning in full shoreline loading operations is proposed. This model seeks to optimize the balance between yard operation instructions and quay crane operation instructions. An enhanced Constrained Optimization Genetic Algorithms-Greedy Randomized Adaptive Search (COGA-GRASP) algorithm is introduced to tackle this decision-making issue, and it is applied to identify the most optimal bay configuration for full shoreline loading operations. The proposed model’s effectiveness is validated through testing and solution outcomes.