A Multi-Objective Genetic Algorithm for Large-Scale Integrated Berth Allocation and Quay Crane Assignment Problem With Maintenance Activities

In the current era of globalization, with increasing vessel cargo and limited port resources, the operational efficiency of container terminals is of paramount importance. Berth allocation and quay crane allocation problems (BACAPs) emerge as pivotal focal points, especially in large-scale container terminals. Although preventive maintenance for quay cranes is crucial for reducing equipment failures and widely implemented in real-world operations, it is often overlooked in existing studies. Lately, few methods are proposed considering maintenance activities. However, their performance are unsatisfied in terms of large-scale problems and hard to meet the requirement of efficiency. To deal with this challenge, in this paper, we present a mixed integer bi-objective optimization model and further propose a novel algorithm to address the large-scale BACAP with quay crane maintenance activities. This model aims to minimize vessel turnaround durations and the penalty of unscheduled maintenance. Meanwhile, based on NSGA-II, the model called RTAA utilizes a novel decoding method withRecurrentTemporal berthAllocation and quay craneAssignment, which can greatly reduce the probability of generating infeasible solutions in a heuristic way. Moreover, the island model is involved to improve the efficiency and parallelism of the model and enhance the diversity of the Pareto-front solutions. Compared to the existing methods in both small and large instances, the RTAA demonstrates its efficacy in discovering superior and more diverse solutions. In particular, for large-scale problems involving 100 vessels, as well as more berths and quay cranes, our model still delivers superior performance with a significant reduction in computation time. Additionally, our approach shows excellent scalability, as it can be easily adapted to scenarios that do not consider maintenance activities.