Clustering algorithms applied to usage related segments of electric vehicle charging stations

Here, a data set collected within the large network of charging stations located in one of the electromobility leading countries the Netherlands, is analysed. The data set consists of more than one million charging transactions that took place in more than 1700 charging stations in the time period of four years. Clustering algorithms such as k-means, dbscan and agglomerative hierarchical clustering are applied to identify usage related segments of charging stations. The selection of features was made based on main classes of factors that are expected to define the use of charging stations (e.g. popularity, temporal characteristics, utilization). The resulting segments of charging stations are compared and interpreted. Better understanding of the charging behaviour of EV users can help improving planning of charging infrastructure and exploitation of smart charging technologies. (C) 2019 The Authors. Published by Elsevier B.V.