SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization
Battery management systems; Charging (batteries); Computer architecture; Digital storage; Heuristic methods; Lithium-ion batteries; Long short-term memory; Temperature measurement; Trees (mathematics); Bidirectional gated recurrent unit; Computational modelling; Deep learning; GRU; Hyper-parameter;...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-27186 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-271862023-05-29T17:40:41Z SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization How D.N.T. Hannan M.A. Lipu M.S.H. Ker P.J. Mansor M. Sahari K.S.M. Muttaqi K.M. 57212923888 7103014445 36518949700 37461740800 6701749037 57218170038 55582332500 Battery management systems; Charging (batteries); Computer architecture; Digital storage; Heuristic methods; Lithium-ion batteries; Long short-term memory; Temperature measurement; Trees (mathematics); Bidirectional gated recurrent unit; Computational modelling; Deep learning; GRU; Hyper-parameter; Learning models; Optimisations; Parzen estimators; State-of-charge estimation; States of charges; Optimization State-of-charge (SOC) is a crucial battery quantity that needs constant monitoring to ensure cell longevity and safe operation. However, SOC is not an observable quantity and cannot be practically measured outside of laboratory environments. Hence, machine learning (ML) has been employed to map correlated observable signals such as voltage, current, and temperature to SOC values. In recent studies, deep learning (DL) has been a prominent ML approach outperforming many existing methods for SOC estimation. However, yielding optimal performance from DL models relies heavily on an appropriate selection of hyperparameters. At present, researchers relied on established heuristics to select hyperparameters through manual tuning or exhaustive search methods such as grid search and random search. This results in lengthy development time in addition to less accurate and inefficient models. This study proposes a systematic and automated approach to hyperparameter selection with a Bayesian optimization strategy known as tree Parzen estimator (TPE) in combination with the Hyperband pruning algorithm. The TPE optimization is run on various DL models such as BGRU, GRU, LSTM, CNN, FCN, and DNN to optimize for the best hyperparameter combination for each architecture. The Hyperband pruning algorithm is used to prune unpromising trials during the TPE run which results in time and computational resource savings. Experiment results show that the best performing model, BGRU-TPE incurs a low computation cost with no compromise in model accuracy, maintaining the best balance of both. The proposed model BGRU-TPE achieves the lowest RMSE and MAE error at 0.8% and 0.56%, respectively on various electric vehicle drive cycles at varying ambient temperatures and maintains a low computational cost at 15 600 FLOPS with the model size of only 193.3 KB. � 1972-2012 IEEE. Final 2023-05-29T09:40:40Z 2023-05-29T09:40:40Z 2022 Article 10.1109/TIA.2022.3180282 2-s2.0-85131715742 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131715742&doi=10.1109%2fTIA.2022.3180282&partnerID=40&md5=151429d136de49ff60ab6dd5a4a59d49 https://irepository.uniten.edu.my/handle/123456789/27186 58 5 6629 6638 Institute of Electrical and Electronics Engineers Inc. Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Battery management systems; Charging (batteries); Computer architecture; Digital storage; Heuristic methods; Lithium-ion batteries; Long short-term memory; Temperature measurement; Trees (mathematics); Bidirectional gated recurrent unit; Computational modelling; Deep learning; GRU; Hyper-parameter; Learning models; Optimisations; Parzen estimators; State-of-charge estimation; States of charges; Optimization |
| author2 |
57212923888 |
| author_facet |
57212923888 How D.N.T. Hannan M.A. Lipu M.S.H. Ker P.J. Mansor M. Sahari K.S.M. Muttaqi K.M. |
| format |
Article |
| author |
How D.N.T. Hannan M.A. Lipu M.S.H. Ker P.J. Mansor M. Sahari K.S.M. Muttaqi K.M. |
| spellingShingle |
How D.N.T. Hannan M.A. Lipu M.S.H. Ker P.J. Mansor M. Sahari K.S.M. Muttaqi K.M. SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| author_sort |
How D.N.T. |
| title |
SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| title_short |
SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| title_full |
SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| title_fullStr |
SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| title_full_unstemmed |
SOC Estimation Using Deep Bidirectional Gated Recurrent Units with Tree Parzen Estimator Hyperparameter Optimization |
| title_sort |
soc estimation using deep bidirectional gated recurrent units with tree parzen estimator hyperparameter optimization |
| publisher |
Institute of Electrical and Electronics Engineers Inc. |
| publishDate |
2023 |
| _version_ |
1806426214152273920 |
| score |
13.214268 |