Port Container Terminal Quay Crane Allocation Based on Simulation and Machine Learning Method

Abstract

Container terminals play a crucial role in exporting and importing goods, where export and import containers are loaded and unloaded. Containers are usually loaded and unloaded with a dock crane. A quay crane is assigned at a container port in advance, considering a ship's arrival schedule. However, allocating a quay crane is difficult owing to the limited number of quay cranes available and the need to consider the shipping timetable. In this study, by considering the schedule of each ship arriving from a container terminal, the number of unloaded containers for each ship, and the limited number of quay cranes, we conduct quay crane assignment through a simulation model to increase the productivity of a container terminal. Alongside, it is evident that artificial intelligence (AI) and machine learning (ML) are necessary for port management in many ways, from berth scheduling to quay allocation. In this study, we also investigate the applicability of ML and metaheuristic approaches in quay allocation problems and explore further possibilities. In this study, we also highlight the sensor-based automation of quay allocation using Internet of Things (IoT) technologies for future research in the domain of port and terminal management.

A Systematic Review of Computer Vision and AI in Parking Space Allocation in a Seaport

“…In contrast to the development of smart cities, which often focuses on enhancing transportation systems inside urban regions, this study investigates the potential of AI and CV as tools for optimizing traffic management and space allocation at seaports [7]. This study aims to shed light on the benefits of AI and CV in managing seaport parking to streamline space allocation and traffic flow.…”

AI-Powered Intelligent Seaport Mobility: Enhancing Container Drayage Efficiency through Computer Vision and Deep Learning

“…First, it underscores the potential of AI and CV, especially deep learning and transfer learning, in enhancing seaport parking systems. By leveraging these advanced techniques, we aim to process the video data from strategically positioned CCTV cameras at seaports, introducing a transformative framework for sustainable parking systems, especially in the context of container drayage operations [3,6]. Second, the research brings to light an innovative model enabled by deep learning, which, when applied to CCTV footage, can provide real-time data on available parking slots, amplifying the efficiency of drayage operations.…”