Hybrid Cuckoo Search for the Capacitated Vehicle Routing Problem

Mansour Alssager,Herman Yuliansyah,Rosmayati Mohemad,Masri Ayob,Zulaiha Ali Othman

doi:10.3390/sym12122088

Abstract

Having the best solution for Vehicle Routing Problem (VRP) is still in demand. Beside, Cuckoo Search (CS) is a popular metaheuristic based on the reproductive strategy of the Cuckoo species and has been successfully applied in various optimizations, including Capacitated Vehicle Routing Problem (CVRP). Although CS and hybrid CS have been proposed for CVRP, the performance of CS is far from the state-of-art. Therefore, this study proposes a hybrid CS with Simulated Annealing (SA) algorithm for the CVRP, consisting of three improvements—the investigation of 12 neighborhood structures, three selections strategy and hybrid it with SA. The experiment was conducted using 16 instances of the Augerat benchmark dataset. The results show that 6 out of 12 neighborhood structures were the best and the disruptive selection strategy is the best strategy. The experiments’ results showed that the proposed method could find optimal and near-optimal solutions compared with state-of-the-art algorithms.

Highlights

Having the best solution for the vehicle routing problem (VRP) is challenging
Experiment 1: First, we investigated the performance of the 12 neighborhood structures to identify the best set of neighborhoods among them and we formed a sequence based on the knowledge obtained
We investigated the performance of the neighborhood structures on a random generated solution

Summary

Introduction

Having the best solution for the vehicle routing problem (VRP) is challenging. It is categorized as a combinatorial optimization problem related to operations research, algorithm theory, and computational complexity theory, which use mathematical and scientific studies with a robust experiment to obtain a reliable solution. Single-based solutions such as tabu search [4] and simulated annealing (SA) [5] have the ability to exploit the search space in a short time and have some limitations such as weak exploration as Lévy flight artificial bee colony algorithm. Hybridization between a population-based and a single-based metaheuristic has been proposed for the CVRP to overcome these two categories’ limitations [15]

Objectives

Methods

Results

Discussion

Conclusion