Solving capacitated vehicle routing problems using edge histogram based sampling algorithms

Abstract

In evolutionary algorithms based on probabilistic modeling, the offspring population is generated according to the estimated probability density model of the parent instead of using recombination and mutation operators. In previous papers, we have proposed an edge histogram based sampling algorithm (EHBSA) based on probabilistic model-building genetic algorithms (PMBGAs) and showed they work well on sequencing problems; the TSP and flow shop scheduling problems. In this paper, we apply EHBSA for solving capacitated vehicle routing problems (CVRP). The results showed EHBSA work fairly well on the CVRP and it also worked better than well-known traditional two-parent recombination operators.