Solution of capacitated vehicle routing problem with invasive weed and hybrid algorithms

Ümit Yıldırım,Yusuf Kuvvetli

doi:10.5267/j.ijiec.2021.4.002

Abstract

The vehicle routing problem is widespread in terms of optimization, which is known as being NP-Hard. In this study, the vehicle routing problem with capacity constraints is solved using cost- and time-efficient metaheuristic methods: an invasive weed optimization algorithm, genetic algorithm, savings algorithm, and hybridized variants. These algorithms are tested using known problem sets in the literature. Twenty-four instances evaluate the performance of algorithms from P and five instances from the CMT data set group. The invasive weed algorithm and its hybrid variant with savings and genetic algorithms are used to determine the best methodology regarding time and cost values. The proposed hybrid approach has found optimal P group problem instances with a 2% difference from the best-known solution on average. Similarly, the CMT group problem is solved with about a 10% difference from the best-known solution on average. That the proposed hybrid solutions have a standard deviation of less than 2% on average from BKS indicates that these approaches are consistent.

Highlights

One of the issues frequently evaluated in logistics problems is the minimization of transportation costs
The invasive weed optimization algorithm (IWO) adapted to the capacitated vehicle routing problem (CVRP) yields exceptionally competitive and efficient results
It is concluded that the savings algorithm generally has the worst success; the performance of both the Genetic algorithms (GAs) and IWO is better than that of the savings algorithm

Summary

Introduction

One of the issues frequently evaluated in logistics problems is the minimization of transportation costs. A hybrid approach consisting of ant colony optimization and the genetic algorithm has been proposed to solve the multi-depot vehicle routing problem (Yücenur & Demirel, 2011). Bozyer et al proposed a heuristic method based on the grouping first and route to solve the capacitated vehicle routing problem (CVRP) (Boyzer, Alkan, & Fığlalı, 2014). The researchers applied the proposed approach to the problem adopted from the literature They demonstrated that they achieve the best-known solutions for most problems with short CPU times. They noted that, according to the results, the performance achieved with the proposed algorithm outperformed some other particle swarm optimization-based approaches.

Methods

Results

Conclusion