Learning-based Pareto-optimum routing of ships incorporating uncertain meteorological and oceanographic forecasts

Yuhan Guo, Yiyang Wang, Yuhan Chen, Lingxiao Wu and Wengang Mao

Transportation Research Part E: Logistics and Transportation Review, 2024, vol. 192, issue C

Abstract: In modern shipping logistics, multi-objective ship route planning has attracted considerable attention in both academia and industry, with a primary focus on energy conservation and emission reduction. The core challenges in this field involve determining the optimal route and sailing speed for a given voyage under complex and variable meteorological and oceanographic conditions. Typically, the objectives revolve around optimizing fuel consumption, carbon emissions, duration time, energy efficiency, and other relevant factors. However, in the multi-objective route planning problem involving variable routes and speeds, the extensive solution space contains a substantial number of unevenly distributed feasible samples. Traditional heuristic optimization techniques, such as multi-objective evolutionary algorithms, which serve as the core component of optimization programs, suffer from inefficiencies in exploring the solution space. Consequently, these algorithms may tend to converge toward local optima during population iteration, resulting in a solution set characterized by sub-optimal convergence and limited diversity. This ultimately undermines the potential benefits of routing optimization. To address such challenging problem in route planning tasks, we propose a self-adaptive intelligent learning network aiming at capturing the potential evolutionary characteristics during population iteration, in order to achieve high-efficiency directed optimization of individuals. Additionally, an uncertainty-driven module is developed by incorporating ensemble forecasts of meteorological and oceanographic variables to form the Pareto frontier with more reliable solutions. Finally, the overall framework of the proposed learning-based multi-objective evolutionary algorithm is meticulously designed and validated through comprehensive analyses. Optimization results demonstrate its superiority in generating routing plans that effectively minimize costs, reduce emissions, and mitigate risks.

Keywords: Ship route planning; Multi-objective optimization; Evolutionary algorithm; Learning-based methods; Forecast uncertainty (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1366554524003776
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:transe:v:192:y:2024:i:c:s1366554524003776

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/600244/bibliographic
http://www.elsevier. ... 600244/bibliographic

DOI: 10.1016/j.tre.2024.103786

Access Statistics for this article

Transportation Research Part E: Logistics and Transportation Review is currently edited by W. Talley

More articles in Transportation Research Part E: Logistics and Transportation Review from Elsevier
Bibliographic data for series maintained by Catherine Liu ().