Discovering EV Charging Site Archetypes Through Few Shot Forecasting: The First U.S.-Wide Study

TL;DR

This study introduces a novel framework combining clustering and few-shot forecasting to identify EV charging site archetypes across the U.S., improving demand prediction at sites with limited data and aiding infrastructure planning.

Contribution

It presents the first large-scale, U.S.-wide analysis of EV charging site archetypes using a new dataset and a combined clustering and few-shot forecasting approach, enhancing demand prediction accuracy.

Findings

Archetype-specific models outperform global baselines in demand forecasting.

Clustering reveals meaningful site categories for targeted infrastructure planning.

The approach supports cost reduction and grid resilience strategies.

Abstract

The decarbonization of transportation relies on the widespread adoption of electric vehicles (EVs), which requires an accurate understanding of charging behavior to ensure cost-effective, grid-resilient infrastructure. Existing work is constrained by small-scale datasets, simple proximity-based modeling of temporal dependencies, and weak generalization to sites with limited operational history. To overcome these limitations, this work proposes a framework that integrates clustering with few-shot forecasting to uncover site archetypes using a novel large-scale dataset of charging demand. The results demonstrate that archetype-specific expert models outperform global baselines in forecasting demand at unseen sites. By establishing forecast performance as a basis for infrastructure segmentation, we generate actionable insights that enable operators to lower costs, optimize energy and pricing strategies, and support grid resilience critical to climate goals.