An ensemble learning based multi-objective evolutionary algorithm for the dynamic vehicle routing problem with time windows

•A multi-objective optimization model for DVRPTW is proposed.•A new DMOEA using ensemble learning is proposed.•A population-based prediction strategy is used to guarantee feasible solutions.•Compared with four other algorithms, EL-DMOEA is effective and promising. The Vehicle Routing Problem (VRP) i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers & industrial engineering Jg. 154; S. 107131
Hauptverfasser: Wang, Feng, Liao, Fanshu, Li, Yixuan, Yan, Xuesong, Chen, Xu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.04.2021
Schlagworte:
Dynamic multi-objective optimization
Dynamic vehicle routing problem
Ensemble learning
Dynamic multi-objective optimization
Dynamic vehicle routing problem
Ensemble learning
ISSN:0360-8352, 1879-0550
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A multi-objective optimization model for DVRPTW is proposed.•A new DMOEA using ensemble learning is proposed.•A population-based prediction strategy is used to guarantee feasible solutions.•Compared with four other algorithms, EL-DMOEA is effective and promising. The Vehicle Routing Problem (VRP) is a typical combinatorial optimization problem and has been studied for many years. However, there are few researches on the Dynamic Vehicle Routing Problem with Time Window (DVRPTW), which is an extension of VRP and more challenging with changing environmental factors, such as stochastic customer requests. Once changes happen, the routes should be adjusted for the new environments. In this paper, we construct a multi-objective optimization model for the DVRPTW and propose a new algorithm named as EL-DMOEA, where an ensemble learning method is investigated to improve the performance of the algorithm. In EL-DMOEA, to enhance the population’s diversity and accelerate the convergence, three different strategies, i.e., population-based prediction strategy, immigrant strategy and random strategy, are employed in the training process of three kinds of basic models respectively. The experimental results on the test benchmarks reveal that the proposed algorithm is effective to make promising routing plans.
ISSN:0360-8352
1879-0550
DOI:10.1016/j.cie.2021.107131