On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters

Yangxiao Xiang; Henry Shu-Hung Chung; Hongjian Lin

doi:10.1109/APEC48139.2024.10509403

On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters

Yangxiao Xiang^*, Henry Shu-Hung Chung, Hongjian Lin

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

Explicit model predictive control (EMPC) has attracted extensive attention in the field of power electronics owing to its excellent dynamic performance. However, the implementation of EMPC in hardware poses considerable challenges as it requires a large amount of computing resources for online computation. In this regard, this paper proposes to use a double-rectified linear unit (DualReLU) artificial neural network (ANN) to approximate EMPC. By taking advantage of the bilaterally bounded property of the offline law distribution in power converter applications, the proposed DualReLU ANN is verified to be able to effectively approximate EMPC while significantly reducing computational load and memory usage requirements. © 2024 IEEE.

Original language	English
Title of host publication	2024 IEEE Applied Power Electronics Conference and Exposition (APEC)
Publisher	IEEE
Pages	2822-2827
ISBN (Electronic)	979-8-3503-1664-3
DOIs	https://doi.org/10.1109/APEC48139.2024.10509403
Publication status	Published - 2024
Event	39th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2024 - Long Beach, United States Duration: 25 Feb 2024 → 29 Feb 2024

Publication series

Name	Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC
ISSN (Print)	1048-2334

Conference

Conference	39th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2024
Place	United States
City	Long Beach
Period	25/02/24 → 29/02/24

Funding

This work was supported by the Green Tech Fund from the Hong Kong Special Administrative Region, China, under Project #GTF202020166

Research Keywords

ANN
model predictive control

Access Output

10.1109/APEC48139.2024.10509403

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Xiang, Y., Chung, H. S.-H., & Lin, H. (2024). On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters. In 2024 IEEE Applied Power Electronics Conference and Exposition (APEC) (pp. 2822-2827). (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC). IEEE. https://doi.org/10.1109/APEC48139.2024.10509403

@inproceedings{6c23a9a0b7744586af7db63618711e14,

title = "On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters",

abstract = "Explicit model predictive control (EMPC) has attracted extensive attention in the field of power electronics owing to its excellent dynamic performance. However, the implementation of EMPC in hardware poses considerable challenges as it requires a large amount of computing resources for online computation. In this regard, this paper proposes to use a double-rectified linear unit (DualReLU) artificial neural network (ANN) to approximate EMPC. By taking advantage of the bilaterally bounded property of the offline law distribution in power converter applications, the proposed DualReLU ANN is verified to be able to effectively approximate EMPC while significantly reducing computational load and memory usage requirements. {\textcopyright} 2024 IEEE.",

keywords = "ANN, model predictive control",

author = "Yangxiao Xiang and Chung, {Henry Shu-Hung} and Hongjian Lin",

year = "2024",

doi = "10.1109/APEC48139.2024.10509403",

language = "English",

series = "Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC",

publisher = "IEEE",

pages = "2822--2827",

booktitle = "2024 IEEE Applied Power Electronics Conference and Exposition (APEC)",

address = "United States",

note = "39th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2024 ; Conference date: 25-02-2024 Through 29-02-2024",

}

Xiang, Y, Chung, HS-H & Lin, H 2024, On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters. in 2024 IEEE Applied Power Electronics Conference and Exposition (APEC). Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC, IEEE, pp. 2822-2827, 39th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2024, Long Beach, United States, 25/02/24. https://doi.org/10.1109/APEC48139.2024.10509403

On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters. / Xiang, Yangxiao; Chung, Henry Shu-Hung; Lin, Hongjian.
2024 IEEE Applied Power Electronics Conference and Exposition (APEC). IEEE, 2024. p. 2822-2827 (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters

AU - Xiang, Yangxiao

AU - Chung, Henry Shu-Hung

AU - Lin, Hongjian

PY - 2024

Y1 - 2024

N2 - Explicit model predictive control (EMPC) has attracted extensive attention in the field of power electronics owing to its excellent dynamic performance. However, the implementation of EMPC in hardware poses considerable challenges as it requires a large amount of computing resources for online computation. In this regard, this paper proposes to use a double-rectified linear unit (DualReLU) artificial neural network (ANN) to approximate EMPC. By taking advantage of the bilaterally bounded property of the offline law distribution in power converter applications, the proposed DualReLU ANN is verified to be able to effectively approximate EMPC while significantly reducing computational load and memory usage requirements. © 2024 IEEE.

AB - Explicit model predictive control (EMPC) has attracted extensive attention in the field of power electronics owing to its excellent dynamic performance. However, the implementation of EMPC in hardware poses considerable challenges as it requires a large amount of computing resources for online computation. In this regard, this paper proposes to use a double-rectified linear unit (DualReLU) artificial neural network (ANN) to approximate EMPC. By taking advantage of the bilaterally bounded property of the offline law distribution in power converter applications, the proposed DualReLU ANN is verified to be able to effectively approximate EMPC while significantly reducing computational load and memory usage requirements. © 2024 IEEE.

KW - ANN

KW - model predictive control

UR - http://www.scopus.com/inward/record.url?scp=85192781385&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85192781385&origin=recordpage

U2 - 10.1109/APEC48139.2024.10509403

DO - 10.1109/APEC48139.2024.10509403

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC

SP - 2822

EP - 2827

BT - 2024 IEEE Applied Power Electronics Conference and Exposition (APEC)

PB - IEEE

T2 - 39th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2024

Y2 - 25 February 2024 through 29 February 2024

ER -

Xiang Y, Chung HSH, Lin H. On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters. In 2024 IEEE Applied Power Electronics Conference and Exposition (APEC). IEEE. 2024. p. 2822-2827. (Conference Proceedings - IEEE Applied Power Electronics Conference and Exposition - APEC). Epub 2024 May 2. doi: 10.1109/APEC48139.2024.10509403

On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GTF_EPD: Smart Power Conditioners Using Second Life Electric Vehicle (EV) Batteries

Cite this

On the Use of DualReLU ANN for Approximating Explicit Model Predictive Control for Buck Converters

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GTF_EPD: Smart Power Conditioners Using Second Life Electric Vehicle (EV) Batteries

Cite this