The optimal stacking of import containers in a terminal reduces the reshuffles during the unloading operations. Knowing the departure date of each container is critical for optimal stacking. However, such a date is rarely known because it depends on various attributes. Therefore, some authors have proposed estimation algorithms using supervised classification. Although supervised classifiers can estimate this dwell time, the variable “dwell time” takes ordered values for this problem, suggesting using ordinal regression algorithms. Thus, we have compared an ordinal regression algorithm (selected from 15) against two supervised classifiers (selected from 30). We have set up two datasets with data collected in a container terminal. We have extracted and evaluated 35 attributes related to the dwell time. Additionally, we have run 21 experiments to evaluate both approaches regarding the mean absolute error modified and the reshuffles. As a result, we have found that the ordinal regression algorithm outperforms the supervised classifiers, reaching the lowest mean absolute error modified in 15 () and the lowest reshuffles in 14 () experiments.
Maritime transport carries out most of the world's commercial activities. One of the elements used for maritime transportation is the container. Before moving to or from a country, containers are stacked in a container terminal, also called container yard. Container terminals perform multiple and complex operations daily. Scientific community pays attention to the container stacking operations in the yard area due to its complexity and relevance in the international commerce. In this work, we solve the problem of optimizing the storage spaces allocation to imported containers by the linear mixed integer programming method. The objective of this work is to solve storage space allocation problem for imported containers, in an acceptable computational time. We use an exact optimization method for the operations of a real container yard. We model this optimization problem mathematically as a generalized assignment problem. We present the mathematical formulation, its solution, as well as the computational experiments.