Η τρισδιάστατη φόρτωση κοντέινερ και η επίλυσή της με τη χρήση ευφυών τεχνικών
Three-dimensional container loading and its solution using intelligent techniques
View/
Keywords
Ευφυείς αλγόριθμοι ; Γενετικοί αλγόριθμοι ; Ενισχυτική μάθηση ; Deep RL ; Αποικία μυρμηγκιών ; Σμήνη σωματιδίων ; 3D bin packing ; Logistics ; Βελτιστοποίηση ; Πρακτικές εφαρμογές ; Πολλαπλοί στόχοι ; ΣυμπεράσματαAbstract
This study explores the application of metaheuristic and intelligent optimization techniques to the Three-Dimensional Bin Packing Problem (3D BPP). It analyzes traditional algorithms such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO), as well as modern machine learning techniques like Artificial Neural Networks (ANNs, CNNs) and Deep Reinforcement Learning (DRL). A comparative performance analysis is conducted based on key metrics, including container utilization, execution time, and robustness under uncertainty. The paper further addresses challenges such as dynamic loading, multi-objective optimization (considering cost, time, and CO₂ footprint), and emerging applications in drones, robotics, and smart logistics. It concludes with recommendations for future research, emphasizing the hybridization of algorithms and their sustainable deployment in real-world environments.
Department
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα ΠληροφορικήςNumber of pages
129Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα