Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger

Meysam Gheisarnejad; Arman Fathollahi; Mohammad Sharifzadeh; Eric Laurendeau; Kamal Al-Haddad

doi:10.1109/TTE.2024.3435763

Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger

Meysam Gheisarnejad
, Arman Fathollahi^*
, Mohammad Sharifzadeh
, Eric Laurendeau
, Kamal Al-Haddad

^*Corresponding author for this work

Department of Electrical and Computer Engineering - Electrical Energy Technology

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

13 Citations (Scopus)

Abstract

Among hybrid multilevel rectifiers (HMRs), packed E-cell appeared as an interesting topology due to the generation of nine-level voltage with minimum active/passive devices, but appropriate control design of PEC rectifier is vital demand to keep capacitors voltages well-regulated even under unbalanced/variable dc loads. Therefore, the backstepping control (BSC) strategy is developed to control a nine-level packed E-cell (PEC9) rectifier to be used as a smart EV charger. Proximal policy optimization (PPO) with actor and critic deep neural networks (ADNNs and CDNNs) is trained to adjust the BSC controller, where the PEC9 rectifier can intelligently deal with asymmetrical/symmetrical dc loads. By maximizing a reward function, the PPO agent tries to find the optimal policy to design the control coefficients of BSC with the aim of regulating the PEC9 capacitor's voltages. The developed BSC based on the PPO tuner is validated using hardware-in-the-loop (HiL) and experimental implementation of the PEC9 rectifier to assess the performance of the proposed control scheme.

Original language	English
Journal	IEEE Transactions on Transportation Electrification
Volume	11
Issue	1
Pages (from-to)	3194-3203
Number of pages	10
ISSN	2332-7782
DOIs	https://doi.org/10.1109/TTE.2024.3435763
Publication status	Published - Feb 2025

Keywords

Backstepping control (BSC)
deep neural network (DNN)
hybrid multilevel rectifiers (HMRs)
nine-level packed E-cell (PEC9)

Access to Document

10.1109/TTE.2024.3435763

Library access?

Check availability with the Royal Danish Library

Cite this

@article{8652800f491e4fe1ba45df4a45aad22f,

title = "Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger",

abstract = "Among hybrid multilevel rectifiers (HMRs), packed E-cell appeared as an interesting topology due to the generation of nine-level voltage with minimum active/passive devices, but appropriate control design of PEC rectifier is vital demand to keep capacitors voltages well-regulated even under unbalanced/variable dc loads. Therefore, the backstepping control (BSC) strategy is developed to control a nine-level packed E-cell (PEC9) rectifier to be used as a smart EV charger. Proximal policy optimization (PPO) with actor and critic deep neural networks (ADNNs and CDNNs) is trained to adjust the BSC controller, where the PEC9 rectifier can intelligently deal with asymmetrical/symmetrical dc loads. By maximizing a reward function, the PPO agent tries to find the optimal policy to design the control coefficients of BSC with the aim of regulating the PEC9 capacitor's voltages. The developed BSC based on the PPO tuner is validated using hardware-in-the-loop (HiL) and experimental implementation of the PEC9 rectifier to assess the performance of the proposed control scheme.",

keywords = "Backstepping control (BSC), deep neural network (DNN), hybrid multilevel rectifiers (HMRs), nine-level packed E-cell (PEC9)",

author = "Meysam Gheisarnejad and Arman Fathollahi and Mohammad Sharifzadeh and Eric Laurendeau and Kamal Al-Haddad",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",

year = "2025",

month = feb,

doi = "10.1109/TTE.2024.3435763",

language = "English",

volume = "11",

pages = "3194--3203",

journal = "IEEE Transactions on Transportation Electrification",

issn = "2332-7782",

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

number = "1",

}

Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger. / Gheisarnejad, Meysam; Fathollahi, Arman; Sharifzadeh, Mohammad et al.
In: IEEE Transactions on Transportation Electrification, Vol. 11, No. 1, 02.2025, p. 3194-3203.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger

AU - Gheisarnejad, Meysam

AU - Fathollahi, Arman

AU - Sharifzadeh, Mohammad

AU - Laurendeau, Eric

AU - Al-Haddad, Kamal

PY - 2025/2

Y1 - 2025/2

N2 - Among hybrid multilevel rectifiers (HMRs), packed E-cell appeared as an interesting topology due to the generation of nine-level voltage with minimum active/passive devices, but appropriate control design of PEC rectifier is vital demand to keep capacitors voltages well-regulated even under unbalanced/variable dc loads. Therefore, the backstepping control (BSC) strategy is developed to control a nine-level packed E-cell (PEC9) rectifier to be used as a smart EV charger. Proximal policy optimization (PPO) with actor and critic deep neural networks (ADNNs and CDNNs) is trained to adjust the BSC controller, where the PEC9 rectifier can intelligently deal with asymmetrical/symmetrical dc loads. By maximizing a reward function, the PPO agent tries to find the optimal policy to design the control coefficients of BSC with the aim of regulating the PEC9 capacitor's voltages. The developed BSC based on the PPO tuner is validated using hardware-in-the-loop (HiL) and experimental implementation of the PEC9 rectifier to assess the performance of the proposed control scheme.

AB - Among hybrid multilevel rectifiers (HMRs), packed E-cell appeared as an interesting topology due to the generation of nine-level voltage with minimum active/passive devices, but appropriate control design of PEC rectifier is vital demand to keep capacitors voltages well-regulated even under unbalanced/variable dc loads. Therefore, the backstepping control (BSC) strategy is developed to control a nine-level packed E-cell (PEC9) rectifier to be used as a smart EV charger. Proximal policy optimization (PPO) with actor and critic deep neural networks (ADNNs and CDNNs) is trained to adjust the BSC controller, where the PEC9 rectifier can intelligently deal with asymmetrical/symmetrical dc loads. By maximizing a reward function, the PPO agent tries to find the optimal policy to design the control coefficients of BSC with the aim of regulating the PEC9 capacitor's voltages. The developed BSC based on the PPO tuner is validated using hardware-in-the-loop (HiL) and experimental implementation of the PEC9 rectifier to assess the performance of the proposed control scheme.

KW - Backstepping control (BSC)

KW - deep neural network (DNN)

KW - hybrid multilevel rectifiers (HMRs)

KW - nine-level packed E-cell (PEC9)

UR - https://www.scopus.com/pages/publications/85200208328

U2 - 10.1109/TTE.2024.3435763

DO - 10.1109/TTE.2024.3435763

M3 - Journal article

AN - SCOPUS:85200208328

SN - 2332-7782

VL - 11

SP - 3194

EP - 3203

JO - IEEE Transactions on Transportation Electrification

JF - IEEE Transactions on Transportation Electrification

IS - 1

ER -

Data-Driven Switching Control Technique Based on Deep Reinforcement Learning for Packed E-Cell as Smart EV Charger

Abstract

Keywords

Access to Document

Library access?

Other files and links

Fingerprint

Cite this