Sisi Zheng1, Jin Sha2,*
1School of Mathematics and Statistics, Huizhou University, Huizhou 516007, Guangdong, China.
2School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang 524088, Guangdong, China.
*Corresponding author:Jin Sha
Abstract
The logistics industry, driven by rapid advancements in information technology and global economic integration, has become a key pillar of economic growth. Ports, as critical nodes in the logistics network, play a vital role in maintaining supply chain efficiency. However, the increasing emphasis on energy efficiency and low-carbon management has made optimizing port operations a significant challenge. This study addresses the container relocation problem (CRP) in ports by integrating optimization algorithms and machine learning techniques. An optimization model is constructed, and key factors influencing relocation operations are identified through attribution analysis. Various machine learning methods, including Random Forest (RF), Extra Trees (ET), Support Vector Machine (SVM), Logistic Regression (LR), and Gradient Boosting Classifier (GBC), are employed to analyze the data, with hyperparameters optimized via grid search. Experimental results indicate that GBC achieves the highest classification accuracy, exceeding 90%. The proposed framework provides an innovative solution to combinatorial optimization problems and supports the logistics industry’s transition towards greener and more efficient operations.
References
[1] Hopfield JJ, Tank DW. “Neural” computation of decisions in optimization problems. Biol Cybern. 1985;52(3):141-52.
[2] Vinyals O, Fortunato M, Jaitly N. Pointer networks. Adv Neural Inf Process Syst. 2015;28:2692-700.
[3] Bogyrbayeva A, Yoon T, Ko H, et al. A deep reinforcement learning approach for solving the traveling salesman problem with drone. Transp Res Part C Emerg Technol. 2023;148:103981.
[4] Tang Y, Ye Z, Chen Y, et al. Regulating the imbalance for the container relocation problem: A deep reinforcement learning approach. Comput Ind Eng. 2024;191:110111.
[5] Zehendner E, Caserta M, Feillet D, et al. An improved mathematical formulation for the blocks relocation problem. Eur J Oper Res. 2015;245(2):415-22.
[6] Galle V, Manshadi VH, Boroujeni SB, et al. The stochastic container relocation problem. Transp Sci. 2018;52(5):1035-58.
[7] Hottung A, Tanaka S, Tierney K. Deep learning assisted heuristic tree search for the container pre-marshalling problem. Comput Oper Res. 2020;113:104781.
[8] Jin X, Duan Z, Song W, et al. Container stacking optimization based on Deep Reinforcement Learning. Eng Appl Artif Intell. 2023;123:106508.
[9] Zhong Z, Xu M, Rodriguez MA, et al. Machine learning-based orchestration of containers: A taxonomy and future directions. ACM Comput Surv. 2022;54(10s):1-35.
[10] Tang Y, Ye Z, Chen Y, et al. Regulating the imbalance for the container relocation problem: A deep reinforcement learning approach. Comput Ind Eng. 2024;191:110111.
How to cite this paper
Research on AI-Empowered Port Container Scheduling Models and Optimization Algorithms
How to cite this paper: Sisi Zheng, Jin Sha. (2025) Research on AI-Empowered Port Container Scheduling Models and Optimization Algorithms. Journal of Applied Mathematics and Computation, 9(2), 114-119.
DOI: http://dx.doi.org/10.26855/jamc.2025.06.003