A Comparison of Clustering Method to Determine Depot Location for a Bike-sharing Operation

Abstract

Bike-sharing schemes have become a popular and environmentally friendly transportation mode. This paper focuses on imbalances caused by problems with insufficient bikes or docking stations in such schemes, which lead to operating costs in terms of total distance due to the need to relocate bikes. Here, a method is proposed, based on cluster analysis, for considering depot location in bike-sharing schemes. The main objective is to reduce operating costs by minimizing the total distance required for relocating bikes. First, a method for predicting demand for bikes is presented. Then, the K-means and WK-means are compared to determine the number and location of depots. The last step is to use this method to compare the total distance required for different depot location options. The results indicate that the proposed method performs well in terms of reducing the total distance required.