A Hybrid Physics-Based and Reinforcement Learning Framework for Electric Vehicle Charging Time Prediction

TL;DR

This paper presents a hybrid framework combining physics-based models and reinforcement learning to accurately predict electric vehicle charging times, accounting for battery health and improving over time with operational data.

Contribution

The paper introduces a novel hybrid prediction framework that integrates a physics-based model with reinforcement learning for EV charging time estimation, enhancing accuracy and robustness.

Findings

Analytical model achieves R^2=98.5% and MAPE=2.1%.

Reinforcement learning model improves to R^2=99.2% and MAPE=1.6%.

Framework improves prediction accuracy by 23% and robustness by 35%.

Abstract

In this paper, we develop a hybrid prediction framework for accurate electric vehicle (EV) charging time estimation, a capability that is critical for trip planning, user satisfaction, and efficient operation of charging infrastructure. We combine a physics-based analytical model with a reinforcement learning (RL) approach. The analytical component captures the nonlinear constant-current/constant-voltage (CC--CV) charging dynamics and explicitly models state-of-health (SoH)--dependent capacity and power fade, providing a reliable baseline when historical data are limited. Building on this foundation, we introduce an RL component that progressively refines charging-time predictions as operational data accumulate, enabling improved long-term adaptation. Both models incorporate SoH degradation to maintain predictive accuracy over the battery lifetime. We evaluate the framework using $5{,}000$ simulated charging sessions calibrated to manufacturer specifications and publicly available EV charging datasets. Our results show that the analytical model achieves $R^{2}=98.5\%$ and $\mathrm{MAPE}=2.1\%$, while the RL model further improves performance to $R^{2}=99.2\%$ and $\mathrm{MAPE}=1.6\%$, corresponding to a $23\%$ accuracy gain and $35\%$ improved robustness to battery aging.