Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure
Abstract
Uncertainty quantification for electric vehicle (EV) charging demand is essential to turn the increasing pressure of EV adoption on power systems into a source of flexibility. We study a large-scale dataset of public charging stations in Scotland, where demand exhibits a hierarchical structure, organized across multiple aggregation levels, from individual charging points to regional and national scales. The charging infrastructure is continuously evolving, with new stations deployed and existing ones occasionally removed, which calls for forecasting and uncertainty quantification methods tailored to this evolving structure. To address these challenges, we combine hierarchical forecasting with recent advances in conformal prediction with missing data. The conformal procedures considered produce valid prediction intervals at every node of the hierarchy and the algorithm CP-MNR-Nested successfully accounts for the time-varying hierarchical structure of the data.
Related
- Warning of infrastructure deformation anomaly through probabilistic analysis of InSAR observations
- Designing battery swapping and charging networks for electric freight transport under demand uncertainty
- A machine-vision framework for electric vehicle charging hole localization based on contour-driven detection and geometric verification
- Learned Control Variates for Rare Grid-Outage Estimation at Electric Vehicle Charging Stations
- SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs
BibTeX
@misc{principato2026probabilistic,
title = {{Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure}},
author = {Guillaume Principato and Yvenn Amara-Ouali and Yannig Goude and Bachir Hamrouche and Jean-Michel Poggi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13588},
eprint = {2610.13588},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13588},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure
AU - Guillaume Principato
AU - Yvenn Amara-Ouali
AU - Yannig Goude
AU - Bachir Hamrouche
AU - Jean-Michel Poggi
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.13588
UR - https://arxiv.org/abs/2610.13588
AB - Uncertainty quantification for electric vehicle (EV) charging demand is essential to turn the increasing pressure of EV adoption on power systems into a source of flexibility. We study a large-scale dataset of public charging stations in Scotland, where demand exhibits a hierarchical structure, organized across multiple aggregation levels, from individual charging points to regional and national scales. The charging infrastructure is continuously evolving, with new stations deployed and existing ones occasionally removed, which calls for forecasting and uncertainty quantification methods tailored to this evolving structure. To address these challenges, we combine hierarchical forecasting with recent advances in conformal prediction with missing data. The conformal procedures considered produce valid prediction intervals at every node of the hierarchy and the algorithm CP-MNR-Nested successfully accounts for the time-varying hierarchical structure of the data.
ER -