Electric vehicle telematics data from Audi e-tron SUVs in the United States

This dataset accompanies the paper, "Graph-based two-level clustering for electric vehicle usage patterns" published in Energy and AI (https://doi.org/10.1016/j.egyai.2025.100539). Please cite the paper when referencing the dataset. Update doesn't change the data, only the author attribution.

It is collected over-the-air from Audi e-tron EVs in the United States. Each measurement includes the timestamp, an anonymized vehicle identification number (VIN), a boolean flag indicating whether the vehicle is at home or away, the odometer reading (mileage), and the battery SOC (\%). The SOC is expressed as a percentage of fully charged capacity. There are 3100 individual vehicles included in the dataset, identified through anonymized VINs. Measurements are sent over-the-air at irregular intervals, but generally when the vehicle status (driving, charging, etc.) changes. Consequently, the number of measurements for each VIN varies, but in total, there are over 10 million measurements.