Treffer: Energy Management in Hybrid Energy Storage Systems for Electric Vehicles: A Reinforcement Learning Approach with Python-Simulink Integration
Title:
Energy Management in Hybrid Energy Storage Systems for Electric Vehicles: A Reinforcement Learning Approach with Python-Simulink Integration
Authors:
Contributors:
Queen's University [Kingston, Canada], GDR SEEDS France & EPE Association
Publisher Information:
CCSD, 2025.
Publication Year:
2025
Collection:
collection:UNIV-COMPIEGNE
collection:ALLIANCE-SU
collection:EPE25
collection:ALLIANCE-SU
collection:EPE25
Subject Terms:
Subject Geographic:
Original Identifier:
HAL: hal-05067916
Document Type:
Konferenz
conferenceObject<br />Conference papers
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/doi/10.34746/epe2025-0342
DOI:
10.34746/epe2025-0342
Access URL:
Rights:
info:eu-repo/semantics/OpenAccess
URL: http://creativecommons.org/licenses/by/
URL: http://creativecommons.org/licenses/by/
Accession Number:
edshal.hal.05067916v1
Database:
HAL
Weitere Informationen
A Reinforcement Learning (RL) algorithm is employed for the energy management of a Hybrid Energy Storage System (HESS) in All Electric Vehicles (AEVs), focusing on enhancing battery life and vehicle mileage. Simulink_gym is used as the interface between Python and Simulink environment to enable seamless communication for efficient simulation and training. The results indicate that the RL-based Energy Management Strategy (EMS) significantly outperforms conventional rule-based strategies by achieving superior power sharing in HESS, leading to enhanced energy efficiency and more balanced utilization of storage components.