Optimizing Electric Vehicle Charging Station Locations: A Data-driven System with Multi-source Fusion

TL;DR

The paper tackles the challenge of strategically locating EV charging infrastructure under rising demand in NSW, Australia. It introduces a data-driven, multi-source fusion system that integrates EV trajectories, geographic context (routes, LGA boundaries, altitude), climate risk (fire/flood), and POIs, and employs an Enhanced DBScan clustering method to identify candidate charging sites. The approach enables per-LGA analyses, aligns suggested sites with existing infrastructure, and provides intuitive Folium-based visualizations to support policymaking. Overall, the method enhances accessibility, safety, and practicality of charging networks and can be adapted to other regions with similar data ecosystems.

Abstract

With the growing electric vehicles (EVs) charging demand, urban planners face the challenges of providing charging infrastructure at optimal locations. For example, range anxiety during long-distance travel and the inadequate distribution of residential charging stations are the major issues many cities face. To achieve reasonable estimation and deployment of the charging demand, we develop a data-driven system based on existing EV trips in New South Wales (NSW) state, Australia, incorporating multiple factors that enhance the geographical feasibility of recommended charging stations. Our system integrates data sources including EV trip data, geographical data such as route data and Local Government Area (LGA) boundaries, as well as features like fire and flood risks, and Points of Interest (POIs). We visualize our results to intuitively demonstrate the findings from our data-driven, multi-source fusion system, and evaluate them through case studies. The outcome of this work can provide a platform for discussion to develop new insights that could be used to give guidance on where to position future EV charging stations.

Figures (7)

• Figure 1: The overview of our data-driven multi-source fusion system for EV charging stations (EVCS) recommendation. We utilize the NSW EV trips with data cleaning and apply the DBScan algorithm to recommend charging station locations according to EV trip points. Additionally, we overlay the fire risk map and display the nearest road segment altitude information for each existing and recommended charging station. We also do a separate analysis for each LGA and align our recommendations to the nearest POIs.
• Figure 2: The overview of EV trip data.
• Figure 3: Existing and approved EV stations, LGA boundaries, route map and altitude.
• Figure 4: Climate change projections map and POIs.
• Figure 5: Visualization of all EV charging stations in NSW.