A nearest centroid classifier based clustering algorithm for solving vehicle routing problem

摘要

A solution is designed for the vehicles to minimize the cost of distribution by which it can supply the goods to the customers with its known capacity can be named as a vehicle routing problem. In Clarke and Wrights saving method and Chopra and Meindl savings matrix method mainly an efficient vehicle routing can be achieved by calculating the distance matrix and savings matrix values based on the customers location or the path where the customer's resides. The main objectives of this paper are to reduce the total distance and the total number of vehicles which is used to deliver the goods to the customers. The proposed algorithm is based on k-means clustering algorithm technique which is used in the data mining scenario effectively. The proposed algorithm decreases the total distance and the number of vehicles assigning to each route. The important thing we need to consider here is that, this new algorithm can enhance the Chopra & Meindl saving matrix method and Clarke and Wright saving matrix method.