Fuzzy C-means clustering based vertical container stacking in container terminals

This study proposes a fuzzy clustering-based vertical stacking strategy (FVSS) to reduce weight variance and enhance operational efficiency in container terminal operations. To address inefficiencies from reshuffling, defined as unnecessary container movements during retrieval, the FVSS method classifies containers into multiple weight classes using Fuzzy C-means (FCM) clustering based on historical container data. Stacking spaces are then proportionally allocated according to cluster sizes, and each stack is assigned a weight reference value to guide real-time container stacking. This enables flexible vertical stacking that dynamically adapts to weight similarities and uncertainty. The proposed strategy was evaluated against existing approaches including hybrid sequence stacking (HSS), random stacking strategy (RSS), and GMM-based methods. Numerical experiments using real-world terminal data demonstrate that FVSS outperforms other strategies, achieving up to 78% reduction in weight variance. Furthermore, performance remains stable even under uncertain weight conditions. These results highlight the practical advantage of integrating fuzzy optimization into stacking strategies, offering a robust and computationally efficient solution for container yard operations.