Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor

Shenyuan Liu; Zhiming Wu; Xiaokai Chen; Zhengyu Li

doi:10.1109/ICMSP58539.2023.10170967

Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor

Shenyuan Liu, Zhiming Wu, Xiaokai Chen^*, Zhengyu Li

^*Corresponding author for this work

School of Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Interest in hybrid electric agricultural tractors (HEAT) is growing as traditional agricultural tractors consume large amounts of non-renewable resources. Energy management strategy (EMS) plays an important role in improving fuel consumption. This paper studies a deep reinforcement learning (DRL)-based EMS for HEAT. The model of HEAT is built and rotary tillage condition is defined for better conformity with the actual situation. Simulation results show that the DRL-based EMS achieves better performance.

Original language	English
Title of host publication	2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1095-1098
Number of pages	4
ISBN (Electronic)	9798350336030
DOIs	https://doi.org/10.1109/ICMSP58539.2023.10170967
Publication status	Published - 2023
Event	5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023 - Chengdu, China Duration: 19 May 2023 → 21 May 2023

Publication series

Name	2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023

Conference

Conference	5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023
Country/Territory	China
City	Chengdu
Period	19/05/23 → 21/05/23

Keywords

Deep Deterministic Policy Gradient
Energy management strategy
hybrid electric agricultural tractors

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICMSP58539.2023.10170967

Cite this

Liu, S., Wu, Z., Chen, X., & Li, Z. (2023). Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor. In 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023 (pp. 1095-1098). (2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMSP58539.2023.10170967

Liu, Shenyuan ; Wu, Zhiming ; Chen, Xiaokai et al. / Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor. 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1095-1098 (2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023).

@inproceedings{7da27274993b4a3ab9e100476467a6d8,

title = "Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor",

abstract = "Interest in hybrid electric agricultural tractors (HEAT) is growing as traditional agricultural tractors consume large amounts of non-renewable resources. Energy management strategy (EMS) plays an important role in improving fuel consumption. This paper studies a deep reinforcement learning (DRL)-based EMS for HEAT. The model of HEAT is built and rotary tillage condition is defined for better conformity with the actual situation. Simulation results show that the DRL-based EMS achieves better performance.",

keywords = "Deep Deterministic Policy Gradient, Energy management strategy, hybrid electric agricultural tractors",

author = "Shenyuan Liu and Zhiming Wu and Xiaokai Chen and Zhengyu Li",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023 ; Conference date: 19-05-2023 Through 21-05-2023",

year = "2023",

doi = "10.1109/ICMSP58539.2023.10170967",

language = "English",

series = "2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023",

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

pages = "1095--1098",

booktitle = "2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023",

address = "United States",

}

Liu, S, Wu, Z, Chen, X & Li, Z 2023, Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor. in 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023. 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1095-1098, 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023, Chengdu, China, 19/05/23. https://doi.org/10.1109/ICMSP58539.2023.10170967

Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor. / Liu, Shenyuan; Wu, Zhiming; Chen, Xiaokai et al.
2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1095-1098 (2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor

AU - Liu, Shenyuan

AU - Wu, Zhiming

AU - Chen, Xiaokai

AU - Li, Zhengyu

PY - 2023

Y1 - 2023

N2 - Interest in hybrid electric agricultural tractors (HEAT) is growing as traditional agricultural tractors consume large amounts of non-renewable resources. Energy management strategy (EMS) plays an important role in improving fuel consumption. This paper studies a deep reinforcement learning (DRL)-based EMS for HEAT. The model of HEAT is built and rotary tillage condition is defined for better conformity with the actual situation. Simulation results show that the DRL-based EMS achieves better performance.

AB - Interest in hybrid electric agricultural tractors (HEAT) is growing as traditional agricultural tractors consume large amounts of non-renewable resources. Energy management strategy (EMS) plays an important role in improving fuel consumption. This paper studies a deep reinforcement learning (DRL)-based EMS for HEAT. The model of HEAT is built and rotary tillage condition is defined for better conformity with the actual situation. Simulation results show that the DRL-based EMS achieves better performance.

KW - Deep Deterministic Policy Gradient

KW - Energy management strategy

KW - hybrid electric agricultural tractors

UR - http://www.scopus.com/inward/record.url?scp=85166264066&partnerID=8YFLogxK

U2 - 10.1109/ICMSP58539.2023.10170967

DO - 10.1109/ICMSP58539.2023.10170967

M3 - Conference contribution

AN - SCOPUS:85166264066

T3 - 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023

SP - 1095

EP - 1098

BT - 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023

Y2 - 19 May 2023 through 21 May 2023

ER -

Liu S, Wu Z, Chen X, Li Z. Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor. In 2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1095-1098. (2023 5th International Conference on Intelligent Control, Measurement and Signal Processing, ICMSP 2023). doi: 10.1109/ICMSP58539.2023.10170967

Deep Reinforcement Learning-Based Energy Management Strategy for Hybrid Electric Agriculture Tractor

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this