Towards an optimal deep neural network for SOC estimation of Electric-Vehicle Lithium-ion battery cells

Muhammad Anjum, Moizzah Asif, Jonathan Williams

Research output: Chapter in Book/Report/Conference proceedingOther chapter contributionpeer-review

Abstract

This paper has identified a minimal configuration of a DNN architecture and hyperparameter settings to effectively estimate SOC of EV battery cells. The results from the experimental work has shown that a minimal configuration of hidden layers and neurons can reduce the computational cost and resources required without compromising the performance. This is further supported by the number of epochs taken to train the best DNN SOC estimations model. Hence, demonstrating that the risk of overfitting estimation models to training datasets can also be reduced. This is further supported by the generalisation capability of the best model demonstrated through the decrease in error metrics values from test phase to those in validation phase.
Original languageEnglish
Title of host publicationEnergy and Sustainable Futures
Subtitle of host publicationProceedings of 2nd ICESF 2020
EditorsIosif Mporas, Pandelis Kourtessis, Amin Al-Habaibeh, Abhishek Asthana, Vladimir Vukovic, John Senior
Place of PublicationHertfordshire
PublisherSpringer
Chapter1
Pages11-18
Number of pages294
Edition1
ISBN (Electronic)978-3-030-63916-7, 978-3-030-63918-1
ISBN (Print)978-3-030-63915-0
DOIs
Publication statusPublished - 4 Nov 2020
EventThe International Conference on Energy and Sustainable Futures (ICESF) - Online, Hertfordshire, United Kingdom
Duration: 10 Sept 202011 Sept 2020

Publication series

NameSpringer Proceedings in Energy
PublisherSpringer International Publishing
ISSN (Print)2352-2534
ISSN (Electronic)2352-2534

Conference

ConferenceThe International Conference on Energy and Sustainable Futures (ICESF)
Abbreviated titleICESF
Country/TerritoryUnited Kingdom
CityHertfordshire
Period10/09/2011/09/20

Fingerprint

Dive into the research topics of 'Towards an optimal deep neural network for SOC estimation of Electric-Vehicle Lithium-ion battery cells'. Together they form a unique fingerprint.

Cite this