State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm

M. S.Hossain Lipu, Afida Ayob, Mohamad Hanif Md Saad, Aini Hussain, Hannan M A, M. Faisal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An accurate state of charge (SOC) estimation for lithium-ion battery has been an intensively researched subject in electric vehicle (EV) application towards the advancement of the sustainable transportation system. However, SOC estimation with high accuracy is challenging because of the complex internal characteristics of the lithium-ion battery which is changed by different environmental situations. This paper develops an accurate method for the state of charge (SOC) estimation of a lithium-ion battery using random forests (RFs) algorithm. However, the accuracy of RFs highly depends on the appropriate selection of trees and leaves per tree in a forest. Thus, this research develops an enhanced model with RFs based gravitational search algorithm (GSA). The aim of GSA is to find the best value of trees and leaves per tree. The robustness and accuracy of the proposed model are tested under different temperatures. The model training and validation are executed using federal urban driving schedule (FUDS). The effectiveness of the proposed method is compared with the conventional RFs and radial basis function neural network (RBFNN) and optimal RBFNN-GSA models using different statistical error terms and computational cost. The proposed RFs based GSA model offers higher robustness and accuracy in reducing RMSE by 55.4%, 67.4%, and MAE by 39.1% and 78.1% than conventional RFs and RBFNN based GSA model, respectively at 25°C.

Original languageEnglish
Title of host publicationIEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018
PublisherIEEE Computer Society
Pages45-50
Number of pages6
Volume2018-October
ISBN (Electronic)9781538656860
DOIs
Publication statusPublished - 6 Dec 2018
Event10th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018 - Kota Kinabalu, Malaysia
Duration: 7 Oct 201810 Oct 2018

Other

Other10th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018
CountryMalaysia
CityKota Kinabalu
Period7/10/1810/10/18

Fingerprint

Neural networks
Electric vehicles
Lithium-ion batteries
Costs
Temperature

Keywords

  • Electric vehicle
  • Gravitational search algorithm
  • Lithium-ion battery
  • Random forests
  • State of charge

ASJC Scopus subject areas

  • Energy Engineering and Power Technology

Cite this

Lipu, M. S. H., Ayob, A., Md Saad, M. H., Hussain, A., M A, H., & Faisal, M. (2018). State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm. In IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018 (Vol. 2018-October, pp. 45-50). [8566648] IEEE Computer Society. https://doi.org/10.1109/APPEEC.2018.8566648

State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm. / Lipu, M. S.Hossain; Ayob, Afida; Md Saad, Mohamad Hanif; Hussain, Aini; M A, Hannan; Faisal, M.

IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018. Vol. 2018-October IEEE Computer Society, 2018. p. 45-50 8566648.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lipu, MSH, Ayob, A, Md Saad, MH, Hussain, A, M A, H & Faisal, M 2018, State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm. in IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018. vol. 2018-October, 8566648, IEEE Computer Society, pp. 45-50, 10th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018, Kota Kinabalu, Malaysia, 7/10/18. https://doi.org/10.1109/APPEEC.2018.8566648
Lipu MSH, Ayob A, Md Saad MH, Hussain A, M A H, Faisal M. State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm. In IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018. Vol. 2018-October. IEEE Computer Society. 2018. p. 45-50. 8566648 https://doi.org/10.1109/APPEEC.2018.8566648
Lipu, M. S.Hossain ; Ayob, Afida ; Md Saad, Mohamad Hanif ; Hussain, Aini ; M A, Hannan ; Faisal, M. / State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm. IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018. Vol. 2018-October IEEE Computer Society, 2018. pp. 45-50
@inproceedings{84eb9f16668e40d9b7e39b2b02ff6d5f,
title = "State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm",
abstract = "An accurate state of charge (SOC) estimation for lithium-ion battery has been an intensively researched subject in electric vehicle (EV) application towards the advancement of the sustainable transportation system. However, SOC estimation with high accuracy is challenging because of the complex internal characteristics of the lithium-ion battery which is changed by different environmental situations. This paper develops an accurate method for the state of charge (SOC) estimation of a lithium-ion battery using random forests (RFs) algorithm. However, the accuracy of RFs highly depends on the appropriate selection of trees and leaves per tree in a forest. Thus, this research develops an enhanced model with RFs based gravitational search algorithm (GSA). The aim of GSA is to find the best value of trees and leaves per tree. The robustness and accuracy of the proposed model are tested under different temperatures. The model training and validation are executed using federal urban driving schedule (FUDS). The effectiveness of the proposed method is compared with the conventional RFs and radial basis function neural network (RBFNN) and optimal RBFNN-GSA models using different statistical error terms and computational cost. The proposed RFs based GSA model offers higher robustness and accuracy in reducing RMSE by 55.4{\%}, 67.4{\%}, and MAE by 39.1{\%} and 78.1{\%} than conventional RFs and RBFNN based GSA model, respectively at 25°C.",
keywords = "Electric vehicle, Gravitational search algorithm, Lithium-ion battery, Random forests, State of charge",
author = "Lipu, {M. S.Hossain} and Afida Ayob and {Md Saad}, {Mohamad Hanif} and Aini Hussain and {M A}, Hannan and M. Faisal",
year = "2018",
month = "12",
day = "6",
doi = "10.1109/APPEEC.2018.8566648",
language = "English",
volume = "2018-October",
pages = "45--50",
booktitle = "IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - State of charge estimation for lithium-ion battery based on random forests technique with gravitational search algorithm

AU - Lipu, M. S.Hossain

AU - Ayob, Afida

AU - Md Saad, Mohamad Hanif

AU - Hussain, Aini

AU - M A, Hannan

AU - Faisal, M.

PY - 2018/12/6

Y1 - 2018/12/6

N2 - An accurate state of charge (SOC) estimation for lithium-ion battery has been an intensively researched subject in electric vehicle (EV) application towards the advancement of the sustainable transportation system. However, SOC estimation with high accuracy is challenging because of the complex internal characteristics of the lithium-ion battery which is changed by different environmental situations. This paper develops an accurate method for the state of charge (SOC) estimation of a lithium-ion battery using random forests (RFs) algorithm. However, the accuracy of RFs highly depends on the appropriate selection of trees and leaves per tree in a forest. Thus, this research develops an enhanced model with RFs based gravitational search algorithm (GSA). The aim of GSA is to find the best value of trees and leaves per tree. The robustness and accuracy of the proposed model are tested under different temperatures. The model training and validation are executed using federal urban driving schedule (FUDS). The effectiveness of the proposed method is compared with the conventional RFs and radial basis function neural network (RBFNN) and optimal RBFNN-GSA models using different statistical error terms and computational cost. The proposed RFs based GSA model offers higher robustness and accuracy in reducing RMSE by 55.4%, 67.4%, and MAE by 39.1% and 78.1% than conventional RFs and RBFNN based GSA model, respectively at 25°C.

AB - An accurate state of charge (SOC) estimation for lithium-ion battery has been an intensively researched subject in electric vehicle (EV) application towards the advancement of the sustainable transportation system. However, SOC estimation with high accuracy is challenging because of the complex internal characteristics of the lithium-ion battery which is changed by different environmental situations. This paper develops an accurate method for the state of charge (SOC) estimation of a lithium-ion battery using random forests (RFs) algorithm. However, the accuracy of RFs highly depends on the appropriate selection of trees and leaves per tree in a forest. Thus, this research develops an enhanced model with RFs based gravitational search algorithm (GSA). The aim of GSA is to find the best value of trees and leaves per tree. The robustness and accuracy of the proposed model are tested under different temperatures. The model training and validation are executed using federal urban driving schedule (FUDS). The effectiveness of the proposed method is compared with the conventional RFs and radial basis function neural network (RBFNN) and optimal RBFNN-GSA models using different statistical error terms and computational cost. The proposed RFs based GSA model offers higher robustness and accuracy in reducing RMSE by 55.4%, 67.4%, and MAE by 39.1% and 78.1% than conventional RFs and RBFNN based GSA model, respectively at 25°C.

KW - Electric vehicle

KW - Gravitational search algorithm

KW - Lithium-ion battery

KW - Random forests

KW - State of charge

UR - http://www.scopus.com/inward/record.url?scp=85060375580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060375580&partnerID=8YFLogxK

U2 - 10.1109/APPEEC.2018.8566648

DO - 10.1109/APPEEC.2018.8566648

M3 - Conference contribution

VL - 2018-October

SP - 45

EP - 50

BT - IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2018

PB - IEEE Computer Society

ER -