The research on two phase pickup vehicle routing based on the K-means++ and genetic algorithms

A popular topic of interest is the development of an efficient vehicle routing plan, which needs to meet customer requirements and ensure delivery with the lowest cost. This paper established a model of the vehicle routing problem with a time window and static network considering the vehicle type, type of goods, and customer satisfaction requirements to build an optimisation model. By optimising the combination of the K-means++ and genetic algorithms, the problem is transformed into a two stage solution, supplier clustering is performed using the K-means++ algorithm, and the vehicle path is determined using the genetic algorithm in each cluster arrangement. Finally, the optimisation results are compared with the actual delivery data, which demonstrates that the optimisation results are superior to the current vehicle arrangement in terms of vehicle utilisation and cost. Finally, an example is presented to illustrate the feasibility of the proposed algorithm.