Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach
This work presents a novel approach to the challenge of battery charging under real-world constraints, related to uncertainties in system parameters and unmeasurable internal states of batteries. By leveraging the imitation learning paradigm, this study introduces an innovative solution to address t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10286476/ |
_version_ | 1797376346076217344 |
---|---|
author | Andrea Pozzi Daniele Toti |
author_facet | Andrea Pozzi Daniele Toti |
author_sort | Andrea Pozzi |
collection | DOAJ |
description | This work presents a novel approach to the challenge of battery charging under real-world constraints, related to uncertainties in system parameters and unmeasurable internal states of batteries. By leveraging the imitation learning paradigm, this study introduces an innovative solution to address the inherent challenges associated with traditional predictive control strategies. A key contribution of this work is the successful application and adaptation of the Dataset Aggregation (DAGGER) algorithm to an “agnostic scenario”, characterized by uncertain battery parameters and unobservable internal states. Furthermore, this work is, to the authors’ best knowledge, the first attempt to amalgamate deep predictive control within the imitation learning framework, offering a fresh perspective and broadening the array of possible solutions to the difficulties in battery charging. Results derived from a realistic battery simulator implementing an electrochemical model demonstrate marked enhancements in battery charging performance, particularly in satisfying temperature constraints. The performance of the proposed algorithm surpasses that of existing approaches, including a benchmark behavioral cloning method based on supervised learning. These advancements highlight the potential of the imitation learning paradigm in tackling complex control problems in battery management systems. |
first_indexed | 2024-03-08T19:37:13Z |
format | Article |
id | doaj.art-4cffea84d58c456ea9f2daa55cbacc87 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-08T19:37:13Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-4cffea84d58c456ea9f2daa55cbacc872023-12-26T00:02:37ZengIEEEIEEE Access2169-35362023-01-011111519011520310.1109/ACCESS.2023.332519410286476Imitation Learning for Agnostic Battery Charging: A DAGGER-Based ApproachAndrea Pozzi0https://orcid.org/0000-0002-9808-5123Daniele Toti1https://orcid.org/0000-0002-9668-6961Faculty of Mathematical, Physical and Natural Sciences, Catholic University of Sacred Heart, Brescia, ItalyFaculty of Mathematical, Physical and Natural Sciences, Catholic University of Sacred Heart, Brescia, ItalyThis work presents a novel approach to the challenge of battery charging under real-world constraints, related to uncertainties in system parameters and unmeasurable internal states of batteries. By leveraging the imitation learning paradigm, this study introduces an innovative solution to address the inherent challenges associated with traditional predictive control strategies. A key contribution of this work is the successful application and adaptation of the Dataset Aggregation (DAGGER) algorithm to an “agnostic scenario”, characterized by uncertain battery parameters and unobservable internal states. Furthermore, this work is, to the authors’ best knowledge, the first attempt to amalgamate deep predictive control within the imitation learning framework, offering a fresh perspective and broadening the array of possible solutions to the difficulties in battery charging. Results derived from a realistic battery simulator implementing an electrochemical model demonstrate marked enhancements in battery charging performance, particularly in satisfying temperature constraints. The performance of the proposed algorithm surpasses that of existing approaches, including a benchmark behavioral cloning method based on supervised learning. These advancements highlight the potential of the imitation learning paradigm in tackling complex control problems in battery management systems.https://ieeexplore.ieee.org/document/10286476/Dataset aggregationdeep neural networksimitation learningoptimal battery chargingpredictive control |
spellingShingle | Andrea Pozzi Daniele Toti Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach IEEE Access Dataset aggregation deep neural networks imitation learning optimal battery charging predictive control |
title | Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach |
title_full | Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach |
title_fullStr | Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach |
title_full_unstemmed | Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach |
title_short | Imitation Learning for Agnostic Battery Charging: A DAGGER-Based Approach |
title_sort | imitation learning for agnostic battery charging a dagger based approach |
topic | Dataset aggregation deep neural networks imitation learning optimal battery charging predictive control |
url | https://ieeexplore.ieee.org/document/10286476/ |
work_keys_str_mv | AT andreapozzi imitationlearningforagnosticbatterychargingadaggerbasedapproach AT danieletoti imitationlearningforagnosticbatterychargingadaggerbasedapproach |