Electric vehicle battery charging with safe-RL

To become the standard power supply for electric vehicles(EVs), Li-ion batteries need balanced current profiles in order to avoidundesirable electrochemical reactions and excessive charging times. Inthis work, we propose a safe exploration deep reinforcement learning(SDRL) approach in order to deter...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Trimboli, Maximiliano, Avila, Luis, Antonelli, Nicolás
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2023
Materias:	Ciencias Informáticas Safe-RL State of Charge Battery aging Variability
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/165927
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-165927
record_format	dspace
spelling	I19-R120-10915-1659272024-05-10T20:05:04Z http://sedici.unlp.edu.ar/handle/10915/165927 Electric vehicle battery charging with safe-RL Trimboli, Maximiliano Avila, Luis Antonelli, Nicolás 2023-09 2023 2024-05-10T18:38:37Z en Ciencias Informáticas Safe-RL State of Charge Battery aging Variability To become the standard power supply for electric vehicles(EVs), Li-ion batteries need balanced current profiles in order to avoidundesirable electrochemical reactions and excessive charging times. Inthis work, we propose a safe exploration deep reinforcement learning(SDRL) approach in order to determine optimal charging profiles undervariable operating conditions. One of the main advantages of reinforce-ment learning (RL) techniques is that they can learn from interactionwith the real or simulated system while incorporating the nonlinear-ity and uncertainty derived from fluctuating environmental conditions.However, since RL techniques have to explore undesirable states beforeobtaining an optimal policy, no safety guarantees are provided. The pro-posed approach aims at maintaining zero constraint violations through-out the learning process by incorporating a safety layer that corrects theaction if a constraint is likely to be violated. Tests performed on theequivalent circuit of a li-ion battery under variability conditions showearly results where SDRL is able to find safe policies while consideringa trade-off between the charging speed and the battery lifespan. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 37-50
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Safe-RL State of Charge Battery aging Variability
spellingShingle	Ciencias Informáticas Safe-RL State of Charge Battery aging Variability Trimboli, Maximiliano Avila, Luis Antonelli, Nicolás Electric vehicle battery charging with safe-RL
topic_facet	Ciencias Informáticas Safe-RL State of Charge Battery aging Variability
description	To become the standard power supply for electric vehicles(EVs), Li-ion batteries need balanced current profiles in order to avoidundesirable electrochemical reactions and excessive charging times. Inthis work, we propose a safe exploration deep reinforcement learning(SDRL) approach in order to determine optimal charging profiles undervariable operating conditions. One of the main advantages of reinforce-ment learning (RL) techniques is that they can learn from interactionwith the real or simulated system while incorporating the nonlinear-ity and uncertainty derived from fluctuating environmental conditions.However, since RL techniques have to explore undesirable states beforeobtaining an optimal policy, no safety guarantees are provided. The pro-posed approach aims at maintaining zero constraint violations through-out the learning process by incorporating a safety layer that corrects theaction if a constraint is likely to be violated. Tests performed on theequivalent circuit of a li-ion battery under variability conditions showearly results where SDRL is able to find safe policies while consideringa trade-off between the charging speed and the battery lifespan.
format	Objeto de conferencia Objeto de conferencia
author	Trimboli, Maximiliano Avila, Luis Antonelli, Nicolás
author_facet	Trimboli, Maximiliano Avila, Luis Antonelli, Nicolás
author_sort	Trimboli, Maximiliano
title	Electric vehicle battery charging with safe-RL
title_short	Electric vehicle battery charging with safe-RL
title_full	Electric vehicle battery charging with safe-RL
title_fullStr	Electric vehicle battery charging with safe-RL
title_full_unstemmed	Electric vehicle battery charging with safe-RL
title_sort	electric vehicle battery charging with safe-rl
publishDate	2023
url	http://sedici.unlp.edu.ar/handle/10915/165927
work_keys_str_mv	AT trimbolimaximiliano electricvehiclebatterychargingwithsaferl AT avilaluis electricvehiclebatterychargingwithsaferl AT antonellinicolas electricvehiclebatterychargingwithsaferl
_version_	1807223106376302592

Electric vehicle battery charging with safe-RL

Ejemplares similares