A logistics path planning method based on K-means clustering and improved genetic algorithm

Abstract

The application provides a logistics path planning method based on K-means clustering and an improved genetic algorithm, and comprises the following steps: clustering n customers, adjusting K values dynamically, selecting K clusters with the best clustering effect, encoding and decoding the K clusters, constructing an initial solution for each cluster s K , calculating the fitness of the population, constructing multiple times for each cluster s K , completing population initialization, judging whether the current population meets the algorithm termination criterion, and outputting the optimal solution of the current population, outputting the optimal solution of the population meeting the algorithm termination criterion, judging whether the improved genetic algorithm traverses all clusters, and performing the next step, otherwise, reinitializing the population, and integrating the optimal solutions of the K clusters to obtain a problem overall solution. According to the application, clustering is performed by using an algorithm, the size of an optimization problem is reduced, a heuristic algorithm is used for optimization calculation, the optimization speed is effectively accelerated, and the solution accuracy is improved.

Images