Hamburger Hafen und Logistik AG (HHLA) is amongst the world’s first ports whose focus is to develop solutions for its Hamburg container terminals using machine learning (ML) to know the dwell time of a container at the terminal. Two projects have already been implemented and running successfully into the IT landscape at Container Terminals Altenwerder (CTA) and Burchardkai (CTB).
At CTA, to increase the productivity of automated block storage, a machine learning (ML) based forecast will be used. It aims at predicting the precise pickup time of a container. While storing any particular container in the yard, its pickup time is usually not known. Optimization of the processes takes place at times when the boxes need not be unnecessarily restacked during its dwell time in the yard. Implementing ML will help the computers in calculating the dwell time for the containers. This uses a traditional data-based algorithm that constantly optimizes itself using state-of-the-art machine learning techniques.
CTB uses a similar approach, where a conventional container yard is used alongside an automated one. Here, too, ML supports terminal steering by granting customized container spaces. Along with the dwell time, the algorithm also helps in calculating the type of delivery. More than the actual data, ML can more appropriately determine whether a container will be loaded onto a truck, ship, or train.
A positive effect is seen at both ends as the containers are stored based on the predicted pickup time, and so should be moved less frequently. The projects were taken to the next level by HHLA and its consulting subsidiary HPC Hamburg Port Consulting.
At the World Artificial Intelligence Conference (WAIC), which took place from July 9–11, 2020, in Shanghai, Angela Titzrath, Chairwoman of the Executive Board of HHLA, highlighted the importance of ML for the company in her welcoming address, “Advancing digitalization is changing the logistics industry and our port business with it. Machine learning solutions provide us with many opportunities to increase productivity and capacity rates at the terminals.” The HHLA Chairwoman also mentioned that ML’s further use cases are yet to be identified.
