Electric Vehicle Charging Load Forecasting: An Experimental Comparison of Machine Learning Methods

2025-12-19

AI Summary

This study addresses the challenge of large-scale electric vehicle (EV) integration for power grid dispatch by systematically evaluating five time-series models—ARIMA, XGBoost, LSTM, TCN, and Transformer—across three temporal granularities (minute-, hour-, and day-level) and three spatial scales (single station, regional, and city-wide). It establishes, for the first time, a unified benchmarking framework spanning a comprehensive spatiotemporal configuration space (3×3 combinations) on multiple real-world datasets. Experimental results delineate the performance boundaries and applicability patterns of each model: shallow models exhibit superior robustness for short-term, fine-grained forecasting, whereas deep learning models increasingly outperform as prediction horizon lengthens and spatial aggregation level rises. The work provides reproducible, comparable empirical evidence to guide scientifically informed model selection for EV charging load forecasting in smart grid applications.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Computer Vision: Large Vision Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

With the growing popularity of electric vehicles as a means of addressing climate change, concerns have emerged regarding their impact on electric grid management. As a result, predicting EV charging demand has become a timely and important research problem. While substantial research has addressed energy load forecasting in transportation, relatively few studies systematically compare multiple forecasting methods across different temporal horizons and spatial aggregation levels in diverse urban settings. This work investigates the effectiveness of five time series forecasting models, ranging from traditional statistical approaches to machine learning and deep learning methods. Forecasting performance is evaluated for short-, mid-, and long-term horizons (on the order of minutes, hours, and days, respectively), and across spatial scales ranging from individual charging stations to regional and city-level aggregations. The analysis is conducted on four publicly available real-world datasets, with results reported independently for each dataset. To the best of our knowledge, this is the first work to systematically evaluate EV charging demand forecasting across such a wide range of temporal horizons and spatial aggregation levels using multiple real-world datasets.

Problem

• Compares EV charging demand forecasting methods across time horizons
• Evaluates forecasting performance at different spatial aggregation levels
• Uses multiple real-world datasets for systematic experimental comparison

Innovation

• Systematically compares five time series forecasting models
• Evaluates performance across multiple temporal and spatial scales
• Uses four real-world datasets for comprehensive experimental analysis