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

arXiv: https://arxiv.org/abs/2512.06287 · HTML: https://mlsanity.com/paper/2512.06287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 5 of 5)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Machine learning pipeline for battery state of health estimation](https://mlsanity.com/paper/2102.00837/) (2021)
- [Rollout-Based Charging Strategy for Electric Trucks with Hours-of-Service Regulations (Extended Version)](https://mlsanity.com/paper/2303.08895/) (2023)
- [Distributed Charging Coordination of Electric Trucks with Limited Charging Resources](https://mlsanity.com/paper/2311.06874/) (2023)
- [Distributed Charging Coordination for Electric Trucks under Limited Facilities and Travel Uncertainties](https://mlsanity.com/paper/2407.10307/) (2024)

## Abstract (arXiv)

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 R2=98.5% and MAPE=2.1%, while the RL model further improves performance to R2=99.2% and MAPE=1.6%, corresponding to a 23% accuracy gain and 35% improved robustness to battery aging.