.png){kind=icon}
.png){kind=icon}
Return
Proactive berth scheduling with data-driven buffer time in container terminals
.png){kind=icon}
PRE
AI
DOI：10.1111/itor.13412.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Global shipment volumes have been increasing due to changes in the business environment of e-commerce and manufacturing. Consequently, container vessels carry more cargo for international trade, increasing uncertainties in terminal management. Terminal operators manage terminals by establishing a proactive schedule that responds to disruptions such as vessel delays, and the introduction of buffer time is a representative proactive strategy. In this study, by analyzing historical delay data with machine learning, we propose data-driven buffer times to consider the heterogeneous arrival uncertainty of vessels. Thus, we proactive scheduling with data-driven buffer times according to the desired robustness levels. This is a novel study on berth scheduling that applies data mining approaches to improve operations research techniques. Numerical experiments were conducted on the berth scheduling with time-invariant quay crane assignment using real-life data to validate the effectiveness of the proposed method. These experimental results revealed that applying the data-driven buffer time could effectively reduce the cost incurred at the terminal by balancing baseline and recovery costs. In addition, our proposed methodology ensured the quality of the solution compared with a stochastic method and reduced the computational burden of a stochastic problem by using the data-driven buffer times obtained prior to the solution construction. Therefore, the proposed method can be introduced into terminal operations to overcome the deficiencies of traditional approaches in terms of academic perspective.
Keywords:
maritime logistics
container terminal operations
berth allocation and quay crane assignment problem
data-driven buffer time
statistical learning
gaussian mixture model
EM-algorithm
rolling-horizon heuristic
Journal
IF:
2.9
Papers:
1.8K
Citations:
3.7K