A data-driven statistical approach for extending electric vehicle charging infrastructure

Abstract

Summary Current trends suggest that there is a substantial increase in the overall usage of electric vehicles (EVs). This, in turn, is causing drastic changes in the transportation industry and, more broadly, in business, policy making, and society. One concrete challenge brought by the increase in the number of EVs is a higher demand for charging stations. This paper presents a methodology to address the challenge of EV charging station deployment. The proposed methodology combines multiple sources of heterogeneous real‐world data for the sake of deriving insights that can be of a great value to decision makers in the field, such as EV charging infrastructure providers and/or local governments. Our starting point is the business data, ie, data describing charging infrastructure, historical data about charging transactions, and information about competitors in the market. Another type of data used are geographical data, such as places of interest located around chargers (eg, hospitals, restaurants, and shops) and driving distances between available chargers. The merged data from different sources are used to predict charging station utilization when EV charging infrastructure and/or contextual data change, eg, when another charging station or a place of interest is created. On the basis of such predictions, we suggest where to deploy new charging stations. We foresee that the proposed methodology can be used by EV charging infrastructure providers and/or local governments as a decision support tool that prescribes an optimal area to place a new charging station while keeping a desired level of utilization of the charging stations. We showcase the proposed methodology with an illustrative example involving the Dutch EV charging infrastructure through the period from 2013 to 2016. Specifically, we prescribe the optimal location for new ELaadNL charging stations based on different objectives such as maximizing the overall charging network utilization and/or increasing the number of chargers in scarcely populated areas.

Electric Vehicles: A Data Science Perspective Review

“…Yes Machine Learning XGBoost, Clustering [36] Clustering [97,98] Optimization Greedy, Genetic [99] Mathematical programming [52,53,100] No Optimization Genetic [101][102][103] Mathematical programming [104][105][106][107] Simulation Queuing theory [51] Agent-based modelling [108,109] He et al [104] proposed a mathematical framework for the macroscopic deployment of charging stations taking into account the equilibrium between demand and supply of energy. User's desire to choose a destination was formulated based on: time, price, and availability of chargers.…”

“…Pevec et al [36] has developed a real-world, data-driven, generic framework for extending EV charging infrastructure. The data used in that framework is from ELaadNL, one of the biggest charging infrastructure providers in the Netherlands.…”

“…• social studies (e.g., influence of sustainable transport on society and environment, such as Tanaka et al [13]); • economics (e.g., market penetration and economical changes due to increase in electric power consumption, such as [6]); • informatics (e.g., computational algorithms for managing charging infrastructure, such as Pevec et al [14], Babic et al [15]); • telecommunications (e.g., protocols for communicating with charging stations or for payment, such as Buamod et al [16] and van Amstel et al [17]); • electrical engineering (e.g., development of low cost batteries, power electronics for the chargers, the motor driver, and improving existing technologies, such as Ruiz et al [18] and Yilmaz et al [19].) This paper is a review which explores EVs from the aspect of three interdisciplinary studies-green transportation, energy informatics, and economics-as depicted in Figure 1.…”

“…Some researchers have developed their own methodology for data gathering. For example, the authors in [14,36] conceptualized data gathering of EV-related data by combining data provided by a company as well as several APIs. The other method is to use existing on-board sensors or to install new sensors for collecting and transmitting the data to the cloud for research purposes.…”

A realistic framework to a greener supply chain for electric vehicles

“…7,8 Also of interest is how to deal with the growing number of EVs. Pevec et al 9 proposed a datadriven approach using predictive analytics to decide optimal charging station locations. Former studies have focused on determining the optimal station locations based on vehicles' movement and driving patterns.…”