EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
1985. Explainable Decision-Making for Stochastic and Dynamic RoRo Ship Operations
Invited abstract in session WB-62: Machine Learning and Optimization in Ports II, stream OR in Port Operations.
Wednesday, 10:30-12:00Room: S12 (building: 101)
Authors (first author is the speaker)
| 1. | Arne Heinold
|
| Department of Operations and Technology, Kühne Logistics University | |
| 2. | Teresa Marquardt
|
| Service Analytics, CAU Kiel University | |
| 3. | Frank Meisel
|
| Christian-Albrechts-University | |
| 4. | Catherine Cleophas
|
| Service Analytics, CAU Kiel University |
Abstract
Our research addresses the loading and unloading problem for Roll-on/Roll-off (RoRo) ships, a critical aspect of maritime logistics. Embracing the complexity of real-world uncertainties, this study explores the impact of varying levels of data availability, facilitated by new telecommunications technologies. Realistic real-world problems face the challenges of stochastic and dynamic aspects, such as uncertainties regarding the type of cargo or process times.
To solve this high-dimensional decision problem, we model it as a sequential decision process and use a hierarchical solution method similar to classification and regression trees (CART). The proposed solution approach yields solutions of short turn-around times but also provides explainability in decision-making. We test our approach against myopic decision policies using real-world scenarios from the Port of Kiel. Subsequently, we apply our methodology to illustrate the influence of different data availability levels, providing specific recommendations regarding the benefits of additional data.
Keywords
- Maritime applications
- Practice of OR
- Decision Support Systems
Status: accepted
Back to the list of papers