Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems

Lithium-ion batteries play a pivotal role in enabling eco-friendly mobility, particularly in electric vehicles, but optimizing their charging process to improve battery lifespan, safety, and overall efficiency remains a significant challenge. Traditional predictive control methods are limited by the...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrea Pozzi, Alessandro Incremona, Daniele Toti
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10973123/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850141314891382784
author Andrea Pozzi
Alessandro Incremona
Daniele Toti
author_facet Andrea Pozzi
Alessandro Incremona
Daniele Toti
author_sort Andrea Pozzi
collection DOAJ
description Lithium-ion batteries play a pivotal role in enabling eco-friendly mobility, particularly in electric vehicles, but optimizing their charging process to improve battery lifespan, safety, and overall efficiency remains a significant challenge. Traditional predictive control methods are limited by their reliance on precise models, which are often hindered by uncertainties in battery parameters due to aging, production variability, and operational conditions. While stochastic predictive control policies can address these uncertainties by incorporating them directly into the optimization process, they typically introduce considerable computational complexity. In response to this challenge, this paper presents a novel approach that adapts imitation learning to efficiently approximate stochastic predictive control strategies, thus significantly reducing the computational burden through offline training. Specifically, the proposed method leverages the Dataset Aggregation algorithm to overcome the issue of distributional shift, a common limitation in imitation learning frameworks. Simulations based on a detailed electrochemical model demonstrate the effectiveness of the method, adhering to probabilistic constraints while offering a scalable and computationally efficient solution for advanced battery management systems.
format Article
id doaj-art-e45725a2ab9644bbbebbd8a185a2568b
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e45725a2ab9644bbbebbd8a185a2568b2025-08-20T02:29:29ZengIEEEIEEE Access2169-35362025-01-0113710417105210.1109/ACCESS.2025.356330010973123Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management SystemsAndrea Pozzi0https://orcid.org/0000-0002-9808-5123Alessandro Incremona1https://orcid.org/0000-0002-6472-0803Daniele Toti2https://orcid.org/0000-0002-9668-6961Faculty of Mathematical, Physical and Natural Sciences, Catholic University of the Sacred Heart, Brescia, ItalyFaculty of Mathematical, Physical and Natural Sciences, Catholic University of the Sacred Heart, Brescia, ItalyFaculty of Mathematical, Physical and Natural Sciences, Catholic University of the Sacred Heart, Brescia, ItalyLithium-ion batteries play a pivotal role in enabling eco-friendly mobility, particularly in electric vehicles, but optimizing their charging process to improve battery lifespan, safety, and overall efficiency remains a significant challenge. Traditional predictive control methods are limited by their reliance on precise models, which are often hindered by uncertainties in battery parameters due to aging, production variability, and operational conditions. While stochastic predictive control policies can address these uncertainties by incorporating them directly into the optimization process, they typically introduce considerable computational complexity. In response to this challenge, this paper presents a novel approach that adapts imitation learning to efficiently approximate stochastic predictive control strategies, thus significantly reducing the computational burden through offline training. Specifically, the proposed method leverages the Dataset Aggregation algorithm to overcome the issue of distributional shift, a common limitation in imitation learning frameworks. Simulations based on a detailed electrochemical model demonstrate the effectiveness of the method, adhering to probabilistic constraints while offering a scalable and computationally efficient solution for advanced battery management systems.https://ieeexplore.ieee.org/document/10973123/Imitation learningneural networksstochastic controlbattery management systems
spellingShingle Andrea Pozzi
Alessandro Incremona
Daniele Toti
Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
IEEE Access
Imitation learning
neural networks
stochastic control
battery management systems
title Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
title_full Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
title_fullStr Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
title_full_unstemmed Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
title_short Neural Network-Based Imitation Learning for Approximating Stochastic Battery Management Systems
title_sort neural network based imitation learning for approximating stochastic battery management systems
topic Imitation learning
neural networks
stochastic control
battery management systems
url https://ieeexplore.ieee.org/document/10973123/
work_keys_str_mv AT andreapozzi neuralnetworkbasedimitationlearningforapproximatingstochasticbatterymanagementsystems
AT alessandroincremona neuralnetworkbasedimitationlearningforapproximatingstochasticbatterymanagementsystems
AT danieletoti neuralnetworkbasedimitationlearningforapproximatingstochasticbatterymanagementsystems