A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning

Ruchen Huang; Hongwen He; Xiangfei Meng; Menglin Li

doi:10.1109/ICECCME52200.2021.9591042

A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning

Ruchen Huang^*, Hongwen He, Xiangfei Meng, Menglin Li

^*Corresponding author for this work

School of Mechanical Engineering

Beijing Institute of Technology

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

5 Citations (Scopus)

Abstract

This paper proposes a novel hierarchical predictive energy management strategy combined with deep reinforcement learning (DRL) for a plug-in hybrid electric bus (PHEB). Firstly, a real-world speed profile is used to train the DDPG algorithm to generate the state of charge (SOC) reference intelligently. Then, a hierarchical model predictive control (MPC) strategy is designed to predict the velocity and allocate energy optimally. At last, the superiority of the proposed strategy is validated under another real-world speed profile. Simulation results indicate that the proposed strategy in this research can reduce the total cost by 10.26% than rule-based strategy.

Original language	English
Title of host publication	International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665412629
DOIs	https://doi.org/10.1109/ICECCME52200.2021.9591042
Publication status	Published - 7 Oct 2021
Event	2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021 - Mauritius, Mauritius Duration: 7 Oct 2021 → 8 Oct 2021

Publication series

Name	International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021

Conference

Conference	2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
Country/Territory	Mauritius
City	Mauritius
Period	7/10/21 → 8/10/21

Keywords

Deep Reinforcement Learning
Energy Management
Intelligent SOC Reference
Model Predictive Control
Plug-in Hybrid Electric Bus

Access to Document

10.1109/ICECCME52200.2021.9591042

Cite this

Huang, R., He, H., Meng, X., & Li, M. (2021). A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning. In International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021 (International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECCME52200.2021.9591042

Huang, Ruchen ; He, Hongwen ; Meng, Xiangfei et al. / A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning. International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021).

@inproceedings{e970f2afbdfe47a4bf31610f93a4382f,

title = "A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning",

abstract = "This paper proposes a novel hierarchical predictive energy management strategy combined with deep reinforcement learning (DRL) for a plug-in hybrid electric bus (PHEB). Firstly, a real-world speed profile is used to train the DDPG algorithm to generate the state of charge (SOC) reference intelligently. Then, a hierarchical model predictive control (MPC) strategy is designed to predict the velocity and allocate energy optimally. At last, the superiority of the proposed strategy is validated under another real-world speed profile. Simulation results indicate that the proposed strategy in this research can reduce the total cost by 10.26\% than rule-based strategy.",

keywords = "Deep Reinforcement Learning, Energy Management, Intelligent SOC Reference, Model Predictive Control, Plug-in Hybrid Electric Bus",

author = "Ruchen Huang and Hongwen He and Xiangfei Meng and Menglin Li",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021 ; Conference date: 07-10-2021 Through 08-10-2021",

year = "2021",

month = oct,

day = "7",

doi = "10.1109/ICECCME52200.2021.9591042",

language = "English",

series = "International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021",

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

booktitle = "International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021",

address = "United States",

}

Huang, R, He, H, Meng, X & Li, M 2021, A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning. in International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021. International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021, Mauritius, Mauritius, 7/10/21. https://doi.org/10.1109/ICECCME52200.2021.9591042

A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning. / Huang, Ruchen; He, Hongwen; Meng, Xiangfei et al.
International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021).

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

TY - GEN

T1 - A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning

AU - Huang, Ruchen

AU - He, Hongwen

AU - Meng, Xiangfei

AU - Li, Menglin

PY - 2021/10/7

Y1 - 2021/10/7

N2 - This paper proposes a novel hierarchical predictive energy management strategy combined with deep reinforcement learning (DRL) for a plug-in hybrid electric bus (PHEB). Firstly, a real-world speed profile is used to train the DDPG algorithm to generate the state of charge (SOC) reference intelligently. Then, a hierarchical model predictive control (MPC) strategy is designed to predict the velocity and allocate energy optimally. At last, the superiority of the proposed strategy is validated under another real-world speed profile. Simulation results indicate that the proposed strategy in this research can reduce the total cost by 10.26% than rule-based strategy.

AB - This paper proposes a novel hierarchical predictive energy management strategy combined with deep reinforcement learning (DRL) for a plug-in hybrid electric bus (PHEB). Firstly, a real-world speed profile is used to train the DDPG algorithm to generate the state of charge (SOC) reference intelligently. Then, a hierarchical model predictive control (MPC) strategy is designed to predict the velocity and allocate energy optimally. At last, the superiority of the proposed strategy is validated under another real-world speed profile. Simulation results indicate that the proposed strategy in this research can reduce the total cost by 10.26% than rule-based strategy.

KW - Deep Reinforcement Learning

KW - Energy Management

KW - Intelligent SOC Reference

KW - Model Predictive Control

KW - Plug-in Hybrid Electric Bus

UR - https://www.scopus.com/pages/publications/85119415538

U2 - 10.1109/ICECCME52200.2021.9591042

DO - 10.1109/ICECCME52200.2021.9591042

M3 - Conference contribution

AN - SCOPUS:85119415538

T3 - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021

BT - International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021

Y2 - 7 October 2021 through 8 October 2021

ER -

Huang R, He H, Meng X, Li M. A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning. In International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021). doi: 10.1109/ICECCME52200.2021.9591042

A novel hierarchical predictive energy management strategy for plug-in hybrid electric bus combined with deep reinforcement learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this