A real-time energy management strategy of flexible smart traction power supply system based on deep Q-learning

Yichen Ying; Zhongbei Tian; Mingli Wu; Qiujiang Liu; Pietro Tricoli

doi:10.1109/TITS.2024.3414446

A real-time energy management strategy of flexible smart traction power supply system based on deep Q-learning

Yichen Ying, Zhongbei Tian^*, Mingli Wu^*, Qiujiang Liu, Pietro Tricoli

^*Corresponding author for this work

Electronic, Electrical and Systems Engineering

Research output: Contribution to journal › Article › peer-review

23 Downloads (Pure)

Abstract

Due to the high degree of controllability of the flexible smart traction power supply system (FSTPSS), day-ahead energy management strategy (DAEMS) was developed to optimize the power flow of the FSTPSS. However, the use of DAEMS is not based on real-time information. For FSTPSS, without real-time information, it cannot solve the problem of planning deviation caused by the real-time fluctuation of uncertain loads or sources. Therefore, this paper proposes a real-time energy management strategy (REMS) which is based on the real-time information to address the problem of planning deviation. REMS is implemented by LSTM and deep Q learning algorithm, where LSTM predicts uncertain loads or sources, and the deep Q-learning controls the operation of FSTPSS based on real-time predicted state. The proposed strategy is validated with the power flow simulation model of TPSS and the real measured data. The simulation results verify the necessity and superiority of the proposed method.

Original language	English
Article number	10570349
Journal	IEEE Transactions on Intelligent Transportation Systems
Early online date	24 Jun 2024
DOIs	https://doi.org/10.1109/TITS.2024.3414446
Publication status	E-pub ahead of print - 24 Jun 2024

Keywords

Real-time information
energy management
planning deviation
deep Q-learning
traction power supply system

Access to Document

10.1109/TITS.2024.3414446

YingY2024real
Y. Ying, Z. Tian, M. Wu, Q. Liu and P. Tricoli, "A Real-Time Energy Management Strategy of Flexible Smart Traction Power Supply System Based on Deep Q-Learning," in IEEE Transactions on Intelligent Transportation Systems, doi: 10.1109/TITS.2024.3414446. © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 1.72 MBLicence: Other (please specify with Rights Statement)

Decarbonising Transport Through Electrification, A Whole System Approach
Tricoli, P. (Principal Investigator) & Roberts, C. (Co-Investigator)
Engineering & Physical Science Research Council
1/09/19 → 31/12/23
Project: Research Councils

Cite this

@article{10178622670849a69b52e117ba909e73,

title = "A real-time energy management strategy of flexible smart traction power supply system based on deep Q-learning",

abstract = "Due to the high degree of controllability of the flexible smart traction power supply system (FSTPSS), day-ahead energy management strategy (DAEMS) was developed to optimize the power flow of the FSTPSS. However, the use of DAEMS is not based on real-time information. For FSTPSS, without real-time information, it cannot solve the problem of planning deviation caused by the real-time fluctuation of uncertain loads or sources. Therefore, this paper proposes a real-time energy management strategy (REMS) which is based on the real-time information to address the problem of planning deviation. REMS is implemented by LSTM and deep Q learning algorithm, where LSTM predicts uncertain loads or sources, and the deep Q-learning controls the operation of FSTPSS based on real-time predicted state. The proposed strategy is validated with the power flow simulation model of TPSS and the real measured data. The simulation results verify the necessity and superiority of the proposed method.",

keywords = "Real-time information, energy management, planning deviation, deep Q-learning, traction power supply system",

author = "Yichen Ying and Zhongbei Tian and Mingli Wu and Qiujiang Liu and Pietro Tricoli",

year = "2024",

month = jun,

day = "24",

doi = "10.1109/TITS.2024.3414446",

language = "English",

journal = "IEEE Transactions on Intelligent Transportation Systems ",

issn = "1558-0016",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - A real-time energy management strategy of flexible smart traction power supply system based on deep Q-learning

AU - Ying, Yichen

AU - Tian, Zhongbei

AU - Wu, Mingli

AU - Liu, Qiujiang

AU - Tricoli, Pietro

PY - 2024/6/24

Y1 - 2024/6/24

N2 - Due to the high degree of controllability of the flexible smart traction power supply system (FSTPSS), day-ahead energy management strategy (DAEMS) was developed to optimize the power flow of the FSTPSS. However, the use of DAEMS is not based on real-time information. For FSTPSS, without real-time information, it cannot solve the problem of planning deviation caused by the real-time fluctuation of uncertain loads or sources. Therefore, this paper proposes a real-time energy management strategy (REMS) which is based on the real-time information to address the problem of planning deviation. REMS is implemented by LSTM and deep Q learning algorithm, where LSTM predicts uncertain loads or sources, and the deep Q-learning controls the operation of FSTPSS based on real-time predicted state. The proposed strategy is validated with the power flow simulation model of TPSS and the real measured data. The simulation results verify the necessity and superiority of the proposed method.

AB - Due to the high degree of controllability of the flexible smart traction power supply system (FSTPSS), day-ahead energy management strategy (DAEMS) was developed to optimize the power flow of the FSTPSS. However, the use of DAEMS is not based on real-time information. For FSTPSS, without real-time information, it cannot solve the problem of planning deviation caused by the real-time fluctuation of uncertain loads or sources. Therefore, this paper proposes a real-time energy management strategy (REMS) which is based on the real-time information to address the problem of planning deviation. REMS is implemented by LSTM and deep Q learning algorithm, where LSTM predicts uncertain loads or sources, and the deep Q-learning controls the operation of FSTPSS based on real-time predicted state. The proposed strategy is validated with the power flow simulation model of TPSS and the real measured data. The simulation results verify the necessity and superiority of the proposed method.

KW - Real-time information

KW - energy management

KW - planning deviation

KW - deep Q-learning

KW - traction power supply system

U2 - 10.1109/TITS.2024.3414446

DO - 10.1109/TITS.2024.3414446

M3 - Article

SN - 1558-0016

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

M1 - 10570349

ER -

A real-time energy management strategy of flexible smart traction power supply system based on deep Q-learning

Abstract

Keywords

Access to Document

Fingerprint

Projects

Decarbonising Transport Through Electrification, A Whole System Approach

Cite this