Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters
This work investigates the effectiveness of deep neural networks within the realm of battery charging. This is done by introducing an innovative control methodology that not only ensures safety and optimizes the charging current, but also substantially reduces the computational complexity with respe...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/9/4404 |
_version_ | 1797601681829003264 |
---|---|
author | Andrea Pozzi Enrico Barbierato Daniele Toti |
author_facet | Andrea Pozzi Enrico Barbierato Daniele Toti |
author_sort | Andrea Pozzi |
collection | DOAJ |
description | This work investigates the effectiveness of deep neural networks within the realm of battery charging. This is done by introducing an innovative control methodology that not only ensures safety and optimizes the charging current, but also substantially reduces the computational complexity with respect to traditional model-based approaches. In addition to their high computational costs, model-based approaches are also hindered by their need to accurately know the model parameters and the internal states of the battery, which are typically unmeasurable in a realistic scenario. In this regard, the deep learning-based methodology described in this work was been applied for the first time to the best of the authors’ knowledge, to scenarios where the battery’s internal states cannot be measured and an estimate of the battery’s parameters is unavailable. The reported results from the statistical validation of such a methodology underline the efficacy of this approach in approximating the optimal charging policy. |
first_indexed | 2024-03-11T04:07:02Z |
format | Article |
id | doaj.art-9bad5210b7d04372aaaca91eb9b500c9 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T04:07:02Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-9bad5210b7d04372aaaca91eb9b500c92023-11-17T23:43:53ZengMDPI AGSensors1424-82202023-04-01239440410.3390/s23094404Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and ParametersAndrea Pozzi0Enrico Barbierato1Daniele Toti2Department of Mathematics and Physics, Catholic University of the Sacred Heart, 25133 Brescia, ItalyDepartment of Mathematics and Physics, Catholic University of the Sacred Heart, 25133 Brescia, ItalyDepartment of Mathematics and Physics, Catholic University of the Sacred Heart, 25133 Brescia, ItalyThis work investigates the effectiveness of deep neural networks within the realm of battery charging. This is done by introducing an innovative control methodology that not only ensures safety and optimizes the charging current, but also substantially reduces the computational complexity with respect to traditional model-based approaches. In addition to their high computational costs, model-based approaches are also hindered by their need to accurately know the model parameters and the internal states of the battery, which are typically unmeasurable in a realistic scenario. In this regard, the deep learning-based methodology described in this work was been applied for the first time to the best of the authors’ knowledge, to scenarios where the battery’s internal states cannot be measured and an estimate of the battery’s parameters is unavailable. The reported results from the statistical validation of such a methodology underline the efficacy of this approach in approximating the optimal charging policy.https://www.mdpi.com/1424-8220/23/9/4404machine learningdeep learningneural networkscomputational complexitypredictive controlbattery management systems |
spellingShingle | Andrea Pozzi Enrico Barbierato Daniele Toti Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters Sensors machine learning deep learning neural networks computational complexity predictive control battery management systems |
title | Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters |
title_full | Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters |
title_fullStr | Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters |
title_full_unstemmed | Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters |
title_short | Optimizing Battery Charging Using Neural Networks in the Presence of Unknown States and Parameters |
title_sort | optimizing battery charging using neural networks in the presence of unknown states and parameters |
topic | machine learning deep learning neural networks computational complexity predictive control battery management systems |
url | https://www.mdpi.com/1424-8220/23/9/4404 |
work_keys_str_mv | AT andreapozzi optimizingbatterychargingusingneuralnetworksinthepresenceofunknownstatesandparameters AT enricobarbierato optimizingbatterychargingusingneuralnetworksinthepresenceofunknownstatesandparameters AT danieletoti optimizingbatterychargingusingneuralnetworksinthepresenceofunknownstatesandparameters |