Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles

Siyu Yue; Yanzhi Wang; Qing Xie; Di Zhu; Massoud Pedram; Naehyuck Chang

doi:10.1109/IECON.2014.7048959

Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles

Siyu Yue, Yanzhi Wang, Qing Xie, Di Zhu, Massoud Pedram, Naehyuck Chang

Research output: Chapter in Book/Entry/Poem › Conference contribution

10 Scopus citations

Abstract

To improve the cycle efficiency and peak output power density of energy storage systems in electric vehicles (EVs), supercapacitors have been proposed as auxiliary energy storage elements to complement the mainstream Lithium-ion (Li-ion) batteries. The performance of such a hybrid electrical energy storage (HEES) system is highly dependent on the implemented management policy. This paper presents a model-free reinforcement learning-based approach to dynamically manage the current flows from and into the battery and supercapacitor banks under various scenarios (combinations of EV specs and driving patterns). Experimental results demonstrate that the proposed approach achieves up to 25% higher efficiency compared to a Li-ion battery only storage system and outperforms other online HEES system control policies in all test cases.

Original language	English (US)
Title of host publication	Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3142-3148
Number of pages	7
ISBN (Print)	9781479940325
DOIs	https://doi.org/10.1109/IECON.2014.7048959
State	Published - Feb 24 2014
Externally published	Yes
Event	40th Annual Conference of the IEEE Industrial Electronics Society, IECON 2014 - Dallas, United States Duration: Oct 30 2014 → Nov 1 2014

Other

Other	40th Annual Conference of the IEEE Industrial Electronics Society, IECON 2014
Country/Territory	United States
City	Dallas
Period	10/30/14 → 11/1/14

Keywords

Electric vehicle
Hybrid energy storage systems
Reinforcement learning

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/IECON.2014.7048959

Cite this

Yue, S., Wang, Y., Xie, Q., Zhu, D., Pedram, M., & Chang, N. (2014). Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles. In Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society (pp. 3142-3148). Article 7048959 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECON.2014.7048959

Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles. / Yue, Siyu; Wang, Yanzhi; Xie, Qing et al.
Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3142-3148 7048959.

Research output: Chapter in Book/Entry/Poem › Conference contribution

Yue, S, Wang, Y, Xie, Q, Zhu, D, Pedram, M & Chang, N 2014, Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles. in Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society., 7048959, Institute of Electrical and Electronics Engineers Inc., pp. 3142-3148, 40th Annual Conference of the IEEE Industrial Electronics Society, IECON 2014, Dallas, United States, 10/30/14. https://doi.org/10.1109/IECON.2014.7048959

@inproceedings{dd6295bf70014a1187c7ae7eccb37310,

title = "Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles",

abstract = "To improve the cycle efficiency and peak output power density of energy storage systems in electric vehicles (EVs), supercapacitors have been proposed as auxiliary energy storage elements to complement the mainstream Lithium-ion (Li-ion) batteries. The performance of such a hybrid electrical energy storage (HEES) system is highly dependent on the implemented management policy. This paper presents a model-free reinforcement learning-based approach to dynamically manage the current flows from and into the battery and supercapacitor banks under various scenarios (combinations of EV specs and driving patterns). Experimental results demonstrate that the proposed approach achieves up to 25% higher efficiency compared to a Li-ion battery only storage system and outperforms other online HEES system control policies in all test cases.",

keywords = "Electric vehicle, Hybrid energy storage systems, Reinforcement learning",

author = "Siyu Yue and Yanzhi Wang and Qing Xie and Di Zhu and Massoud Pedram and Naehyuck Chang",

year = "2014",

month = feb,

day = "24",

doi = "10.1109/IECON.2014.7048959",

language = "English (US)",

isbn = "9781479940325",

pages = "3142--3148",

booktitle = "Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "40th Annual Conference of the IEEE Industrial Electronics Society, IECON 2014 ; Conference date: 30-10-2014 Through 01-11-2014",

}

TY - GEN

T1 - Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles

AU - Yue, Siyu

AU - Wang, Yanzhi

AU - Xie, Qing

AU - Zhu, Di

AU - Pedram, Massoud

AU - Chang, Naehyuck

PY - 2014/2/24

Y1 - 2014/2/24

N2 - To improve the cycle efficiency and peak output power density of energy storage systems in electric vehicles (EVs), supercapacitors have been proposed as auxiliary energy storage elements to complement the mainstream Lithium-ion (Li-ion) batteries. The performance of such a hybrid electrical energy storage (HEES) system is highly dependent on the implemented management policy. This paper presents a model-free reinforcement learning-based approach to dynamically manage the current flows from and into the battery and supercapacitor banks under various scenarios (combinations of EV specs and driving patterns). Experimental results demonstrate that the proposed approach achieves up to 25% higher efficiency compared to a Li-ion battery only storage system and outperforms other online HEES system control policies in all test cases.

AB - To improve the cycle efficiency and peak output power density of energy storage systems in electric vehicles (EVs), supercapacitors have been proposed as auxiliary energy storage elements to complement the mainstream Lithium-ion (Li-ion) batteries. The performance of such a hybrid electrical energy storage (HEES) system is highly dependent on the implemented management policy. This paper presents a model-free reinforcement learning-based approach to dynamically manage the current flows from and into the battery and supercapacitor banks under various scenarios (combinations of EV specs and driving patterns). Experimental results demonstrate that the proposed approach achieves up to 25% higher efficiency compared to a Li-ion battery only storage system and outperforms other online HEES system control policies in all test cases.

KW - Electric vehicle

KW - Hybrid energy storage systems

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=84949928781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949928781&partnerID=8YFLogxK

U2 - 10.1109/IECON.2014.7048959

DO - 10.1109/IECON.2014.7048959

M3 - Conference contribution

AN - SCOPUS:84949928781

SN - 9781479940325

SP - 3142

EP - 3148

BT - Proceedings, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 40th Annual Conference of the IEEE Industrial Electronics Society, IECON 2014

Y2 - 30 October 2014 through 1 November 2014

ER -

Model-free learning-based online management of hybrid electrical energy storage systems in electric vehicles

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this