# Energy Consumption and Battery Aging Minimization Using a Q-learning Strategy for a Battery/Ultracapacitor Electric Vehicle

**Authors:** Bin Xu, Junzhe Shi, Sixu Li, Huayi Li, Zhe Wang  
**arXiv:** [2010.14115](https://arxiv.org/abs/2010.14115)  
**Date:** 2020-10-27  
**Summary page:** https://www.summarizepaper.com/en/paper/2010.14115v1/

## Key points

- The automotive industry is undergoing a revolution in propulsion system electrification
- A study proposes a Q-learning-based strategy to minimize battery degradation and energy consumption in battery/supercapacitor electric vehicles
- Two heuristic energy management methods are also proposed and optimized using Particle Swarm Optimization algorithm
- A vehicle propulsion system model is presented that considers the severity factor battery degradation model and is experimentally validated with the help of Genetic Algorithm
- Q-learning strategy slows down battery degradation by 13-20% and increases vehicle range by 1.5-2% compared to the baseline vehicle without ultracapacitor
- The proposed approach could have significant implications for improving electric vehicle performance while minimizing battery aging effects.

## Summary

The automotive industry has been undergoing a revolution in propulsion system electrification, which improves energy efficiency and reduces dependence on fossil fuels. To address the issue of battery degradation during vehicle operation and lack of research regarding energy consumption in battery/supercapacitor electric vehicles, a study proposes a Q-learning-based strategy to minimize battery degradation and energy consumption. In addition to Q-learning, two heuristic energy management methods are also proposed and optimized using Particle Swarm Optimization algorithm. A vehicle propulsion system model is presented that considers the severity factor battery degradation model and is experimentally validated with the help of Genetic Algorithm. In the results analysis, Q-learning is first explained with the optimal policy map after learning. Then, the result from a vehicle without ultracapacitor is used as the baseline which is compared with the results from the vehicle with ultracapacitor using Q-learning and two heuristic methods as energy management strategies. At the learning and validation driving cycles it was found that the Q-learning strategy slows down battery degradation by 13-20% and increases vehicle range by 1.5-2% compared to the baseline vehicle without ultracapacitor. The study's authors include Bin Xu, Junzhe Shi, Sixu Li, Huayi Li, and Zhe Wang. The proposed approach could have significant implications for improving electric vehicle performance while minimizing battery aging effects.