<![CDATA[Efficient vessel scheduling is crucial to the performance and profitability of maritime terminals, yet conventional approaches often struggle to accommodate the dynamic, nonlinear interactions among vessel arrivals, cargo handling requirements, and berth availability. This study presents a Multilayer Perceptron (MLP)–based scheduling framework that models these complex relationships and delivers actionable berth assignments in real time. Leveraging an integrated dataset of historical arrival and departure timestamps, cargo throughput, and occupancy records, the MLP model was trained on 80% of the data and rigorously tested on the remaining 20% Performance was assessed using metrics such as vessel turnaround time, berth utilization rate, and scheduling accuracy. Experimental results reveal that our MLP-driven scheduler achieves a 15% reduction in average turnaround time and a 12% increase in berth utilization. Remarkably, the neural network maintains high levels of schedule adherence even under peak-demand scenarios, minimizing idle berth time and streamlining cargo flow. These findings underscore the adaptability of advanced machine learning techniques to the evolving demands of port operations.]]>
Copyrights © 2025
