K-Means Clustering and Genetic Algorithm to Solve Vehicle Routing Problem with Time Windows Problem

Abstract

<span lang="EN-US">Distribution is an important aspect of industrial activity to serve customers on time with minimal operational cost. Therefore, it is necessary to design a quick and accurate distribution route. One of them can be design travel distribution route using the k-means method and genetic algorithms. This research will combine k-means method and genetic algorithm to solve VRPTW problem. K-means can do clustering properly and genetic algorithms can optimize the route. The proposed genetic algorithm employs initialize chromosome from the result of k-means and using replacement method of selection. Based on the comparison between genetic algorithm and hybrid k-means genetic algorithm proves that k-means genetic algorithm is a suitable combination method with relative low computation time, are the comparison between 2700 and 3900 seconds.</span>

Hybrid Genetic Algorithms and Simulated Annealing for Multi-trip Vehicle Routing Problem with Time Windows

“…In GA-SA1, populations re-optimized by the simulated annealing algorithm are just the best and worst fitness chromosomes, but in GA-SA4, the population is 10% of the population with the best chromosomes, the more chromosomes optimized by the simuated annealing algorithm, the faster the chance of the algorithm to find the most optimal fitness. Futher research, to needs K-Means for clustering nodes that can improve computation time [30].…”

Challenges and Opportunities for Applying Meta-Heuristic Methods in Vehicle Routing Problems: A Review

“…In large cases, determining vehicle allocation for each consumer and simultaneously determining the route for each vehicle requires quite a lot of computing time. In the study on VRPTW completion, the K-Means clustering method is used to group consumers first, and then look for routes for vehicles that serve consumers in one group [33].…”

Evaluation of popular path planning algorithms

“…The GA seeks to find the optimal result rather than the best one [27]. The problem is first modeled, and the GA's parameters and working logic are determined accordingly.…”