Optimization Subproblem Importance Analysis Based on Machine Learning Prediction in a Three Stage-Export Container Scheduling

Aug 4, 2026

Upload by Ophelia

A scheduling problem for export containers considers how to measure the importance of optimization subproblems across multiple stages in a terminal. The approach models yard crane, internal truck, and quay crane scheduling as subproblems and predicts the overall makespan using each stage’s processing time statistics (mean and standard deviation) together with selected scheduling rules. Numerical experiments show that quay crane and internal truck rule choices drive system performance most strongly. The findings indicate that subproblems contribute unevenly, enabling operators to shift optimization focus and reduce computational complexity via a data-driven framework for interdependency understanding.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Motivation: importance of optimization subproblems

Limitations of conventional integrated optimization

Machine learning for system behavior prediction

Study scope and problem setting

[Available online at www.sciencedirect.com](Available online at www.sciencedirect.com) ScienceDirect Procedia Computer Science 269 (2025) 1389–1397 The 10th International Conference on Computer Science and Computational Intelligence 2025 Optimization subproblem importance analysis based on machine learning prediction in a three stage-export container scheduling Aditya Saputraa,b , Ivan Kristianto Singgihb,c,d,e, * aPT Insera Sena, Sidoarjo, Indonesia bStudy Program of Industrial Engineering, University of Surabaya, Surabaya, Indonesia c The Indonesian Researcher Association in South Korea (APIK), Seoul, 07342, South Korea dKolaborasi Riset dan Inovasi Industri Kecerdasan Artifisial (KORIKA), Jakarta, Indonesia eIndonesia Artificial Intelligence Society, Jakarta 12930, Indonesia Abstract A traditional way to optimize a complex optimization problem is to divide the problem into several subproblems and solve each subproblem separately or another problem that consists of some subproblems. Despite many attempts to define and solve various optimization problems in the container terminal logistics field, how to measure the importance of each subproblem is often ignored in many studies and remains a difficult issue. Most studies directly propose methods to solve a specific subproblem after stating the importance of the specific subproblem, with or without simply considering the effect of other subproblems as input. The advancement of machine learning techniques allows a new paradigm for understanding the importance of such optimization subproblems. In this study, a scheduling problem for export containers in a terminal is considered. The case considers scheduling subproblems on subsequent processing stages on yard cranes, internal trucks, and quay cranes. With the input of each stage’s processing time information (mean and standard deviation values) and the selected scheduling rule for each stage, the makespan of all containers’ processing is predicted. The numerical experiments show that the scheduling rules for quay cranes and internal trucks have the most significant impact on system performance. These finding challenges conventional approaches by revealing that not all subproblems contribute equally to system optimization. The proposed machine learning framework enables terminal operators to adapt their optimization focus to address high-impact areas, reducing computational complexity while providing a data-driven methodology for understanding interdependencies between operational components . © 2025 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ([https://creativecommons.org/licenses/by-nc-nd/4.0](https://creativecommons.org/licenses/by-nc-nd/4.0)) Peer-review under responsibility of the scientific committee of the 10th International Conference on Computer Science and Computational Intelligence (ICCSCI) 2025 Keywords: regression machine learning; rule; container terminal; scheduling * Corresponding author. Tel.: +62-31-298-1392. E-mail address: [ivanksinggih@staff.ubaya.ac.id](ivanksinggih@staff.ubaya.ac.id) 1877-0509 © 2025 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ([https://creativecommons.org/licenses/by-nc-nd/4.0](https://creativecommons.org/licenses/by-nc-nd/4.0)) Peer-review under responsibility of the scientific committee of the 10th International Conference on Computer Science and Computational Intelligence (ICCSCI) 2025 10.1016/j.procs.2025.09.080 1390 Aditya Saputra et al. / Procedia Computer Science 269 (2025) 1389–1397 1. Introduction Recent review on container terminal logistics focused solely on defining various optimization problems and solving them. Even though various integrated problems, starting from the gate operation management up to the seaside operation, have been studied extensively [1,2], none of them could identify which subproblem is more im

FAQs

Why is measuring the importance of optimization subproblems important in container terminal logistics?

Most studies solve subproblems independently after assuming their importance, making it hard to know which subproblems most affect overall system optimization. Without identifying key subproblems, the whole system may only reach local optima due to conflicting decisions.

How is the three-stage export container scheduling problem defined in the study?

It models scheduling subproblems across subsequent processing stages: yard cranes, internal trucks, and quay cranes. Each stage uses processing time information and a chosen scheduling rule to predict the system makespan.

Which scheduling stages have the largest impact on system performance?

The scheduling rules for quay cranes and internal trucks have the most significant impact on overall system performance, indicating that not all subproblems contribute equally.

Aug 4, 2026

Upload by Ophelia