A Prescriptive Analytics Approach for Port Logistics Planning

Port management is critical to the maritime transportation industry. Effective port management aims, among other things, to reduce the amount of time required to operate the cargo volume of the vessels. Numerous uncertainty factors, such as weather and mechanical issues, frequently affect maritime transportation, which can hamper port operations planning. The lack of certainty surrounding a number of relevant parameters makes efficient preparation for quayside operations difficult. As a result, when making decisions, it is critical to account for the possibility of uncertainty. The ability to deal with unfavorable and unpredictable events is one of the characteristics of a great practical solution. In this paper, we investigate a scenario in which machine learning techniques are used to predict data for both the berth allocation and the quay crane assignment problems. We model the problem as a mixed integer linear program with multiple objectives that takes berth allocation and quay crane assignment into account. We propose a genetic algorithm scheme to solve the problem. Crossover and mutation procedures are provided. Finally, managerial implications and future research directions are given.