Path Planning Algorithm for the Multiple Depot Vehicle Routing Problem Based on Parallel Clustering

Abstract

It is necessary to study the problem of vehicle routing in multidistribution centers to improve the speed, time, and cost thereof. It is preferable to use as few vehicles as possible to complete the delivery of goods and minimize the total mileage. With the development of artificial intelligence technology, machine learning is usually used to solve the problem of k shortest paths in multiple distribution centers. User needs are constantly changing; the iterative convergence speed of traditional machine learning methods is low and cannot meet the requirements of path planning in a big-data environment. Aiming at difficult problems in multipath planning, the parallel characteristics of traditional machine learning algorithms are fully exploited; k-means clustering and simulated annealing algorithms are improved through the distributed computing; and the multiple depot vehicle routing problem clustering analysis and path planning under the framework of Spark distributed computing are proposed. Through 30 simulation experiments on the TSPLIB dataset, the optimal solution is obtained with a 100% accuracy rate in problem solving. Experimental comparison and analysis show that the algorithm proposed in this article can solve the problem at least twice as fast as other parallel algorithms. This finding verifies that this method can effectively solve the multipath planning problem, thus greatly improving the quality and efficiency of path planning in large-scale logistics.