Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems

TL;DR

This paper introduces GANCP, a deep learning method that predicts vehicle routing costs to efficiently solve hierarchical vehicle routing problems like MDVRP and CLRP, reducing computational effort.

Contribution

The paper presents a novel neural cost predictor integrated with genetic algorithms to efficiently approximate routing costs without solving each problem explicitly.

Findings

GANCP accurately predicts routing costs, reducing computation time.

The approach yields high-quality solutions on benchmark instances.

It accelerates algorithm development for complex hierarchical routing problems.

Abstract

When vehicle routing decisions are intertwined with higher-level decisions, the resulting optimization problems pose significant challenges for computation. Examples are the multi-depot vehicle routing problem (MDVRP), where customers are assigned to depots before delivery, and the capacitated location routing problem (CLRP), where the locations of depots should be determined first. A simple and straightforward approach for such hierarchical problems would be to separate the higher-level decisions from the complicated vehicle routing decisions. For each higher-level decision candidate, we may evaluate the underlying vehicle routing problems to assess the candidate. As this approach requires solving vehicle routing problems multiple times, it has been regarded as impractical in most cases. We propose a novel deep-learning-based approach called Genetic Algorithm with Neural Cost Predictor (GANCP) to tackle the challenge and simplify algorithm developments. For each higher-level decision candidate, we predict the objective function values of the underlying vehicle routing problems using a pre-trained graph neural network without actually solving the routing problems. In particular, our proposed neural network learns the objective values of the HGS-CVRP open-source package that solves capacitated vehicle routing problems. Our numerical experiments show that this simplified approach is effective and efficient in generating high-quality solutions for both MDVRP and CLRP and has the potential to expedite algorithm developments for complicated hierarchical problems. We provide computational results evaluated in the standard benchmark instances used in the literature.