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

2025-10-30

AI Summary

Existing electric vehicle (EV) charging demand forecasting methods suffer from limited historical data, simplistic temporal modeling, and poor generalization—especially for newly deployed charging stations. To address these limitations, this paper proposes a novel framework integrating clustering with few-shot time-series forecasting. We first identify behavioral archetypes of charging stations at a nationwide scale in the U.S., then construct archetype-specific expert models, establishing an infrastructure segmentation paradigm driven by predictive performance. Experimental results demonstrate that our method achieves significantly higher forecasting accuracy on unseen stations compared to global baseline models. The framework provides actionable decision support for charging operators in energy scheduling, dynamic pricing, and cost management. By enabling more accurate and adaptive demand forecasting—particularly for short-history sites—it contributes to enhanced grid resilience and the advancement of low-carbon transportation systems.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: The sharing economy
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising

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.

Problem

• Forecasting EV charging demand using large-scale data
• Identifying site archetypes through clustering and few-shot learning
• Improving infrastructure planning and grid resilience strategies

Innovation

• Clustering integrates with few-shot forecasting
• Uses novel large-scale charging demand dataset
• Archetype-specific models outperform global baselines