A new analytical framework for the location selection of shared car site

摘要

Reasonable and effective sharing of vehicle location plans will be of great significance for improving the overall efficiency of shared vehicles and the allocation of urban transportation infrastructure resources.This paper predicts the demand for shared cars in Hangzhou by evaluating the ownership rate of shared cars,and estimates the maximum number of people that can be served at each level.Then,using K-means clustering method,the initial clustering center is selected according to the center of gravity method,and the clustering condition is formed by using the minimum distance from each vehicle demand point to the clustering center to form a clustering cluster.The number of service groups of the cluster is added,and the cluster center iteration is performed according to whether each cluster satisfies the number of service groups until the optimal number and location of the network points are obtained.Finally,according to the number of service persons,the construction scale of 12 selected outlets will be determined,and the plan for the location selection of shared car outlets in downtown Hangzhou will be obtained.The research results show that this method can provide an effective basis for the decision-making of shared car site selection.