Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems

Kangshi Wang; Jieming Ma; Ka Lok Man; Kaizhu Huang; Xiaowei Huang

doi:10.1109/EEEIC/ICPSEurope51590.2021.9584526

Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems

Kangshi Wang^*
, Jieming Ma
, Ka Lok Man
, Kaizhu Huang
, Xiaowei Huang

^*Corresponding author for this work

University of Liverpool

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

5 Citations (Scopus)

Abstract

Simulations are widely used in the field of photovoltaic systems as they provide an abundant source of data for the building and training of numerical methods or artificial intelligence techniques. However, the strategies that succeed in simulation may not be victoriously transferred to the real world due to the modeling errors. In this paper, we propose a Gaussian process regression with domain randomization, which is able to bridge the 'Sim-to-Real' gap in the application of maximum power point estimation. By randomizing the parameters of the models for the training process, the Gaussian process regression models can minimize the 'Sim-to-Real' transfer cost and adapt the dynamics of the real-world environment.

Original language	English
Title of host publication	2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)
Editors	Zbigniew M. Leonowicz
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781665436120
DOIs	https://doi.org/10.1109/EEEIC/ICPSEurope51590.2021.9584526
Publication status	Published - 2021
Event	21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Bari, Italy Duration: 7 Sept 2021 → 10 Sept 2021

Publication series

Name	21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings

Conference

Conference	21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021
Country/Territory	Italy
City	Bari
Period	7/09/21 → 10/09/21

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Gaussian process regression
dynamics randomization
maximum power point estimation
photovoltaic systems

Access to Document

10.1109/EEEIC/ICPSEurope51590.2021.9584526

Cite this

Wang, K., Ma, J., Man, K. L., Huang, K., & Huang, X. (2021). Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems. In Z. M. Leonowicz (Ed.), 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe) (pp. 1-4). (21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EEEIC/ICPSEurope51590.2021.9584526

Wang, Kangshi ; Ma, Jieming ; Man, Ka Lok et al. / Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems. 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). editor / Zbigniew M. Leonowicz. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 1-4 (21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings).

@inproceedings{aaab6807473d4321a4989edb8ec1f4de,

title = "Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems",

abstract = "Simulations are widely used in the field of photovoltaic systems as they provide an abundant source of data for the building and training of numerical methods or artificial intelligence techniques. However, the strategies that succeed in simulation may not be victoriously transferred to the real world due to the modeling errors. In this paper, we propose a Gaussian process regression with domain randomization, which is able to bridge the 'Sim-to-Real' gap in the application of maximum power point estimation. By randomizing the parameters of the models for the training process, the Gaussian process regression models can minimize the 'Sim-to-Real' transfer cost and adapt the dynamics of the real-world environment.",

keywords = "Gaussian process regression, dynamics randomization, maximum power point estimation, photovoltaic systems",

author = "Kangshi Wang and Jieming Ma and Man, \{Ka Lok\} and Kaizhu Huang and Xiaowei Huang",

note = "Funding Information: This research is supported by the Natural Science Foundation of China (Grant No. 61702353,62002296), the Natural Science Foundation of Jiangsu Province (Grant No. BK20200250), the Suzhou Science and Technology Project-Key Industrial Technology Innovation (Grant No. SYG202006), Qing Lan Project of Jiangsu Province, the Key Program Special Fund of Xi{\textquoteright}an Jiaotong-Liverpool University (XJTLU), Suzhou, China (Grant No. KSF-A-19, KSF-E-65, KSF-P-02, KSF-E-54), the XJTLU Research Development Fund (Grant No. RDF-17-02-04), and the XJTLU Postgraduate Research Scholarship (Grand No. PGRS1906004). Publisher Copyright: {\textcopyright} 2021 IEEE; 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 ; Conference date: 07-09-2021 Through 10-09-2021",

year = "2021",

doi = "10.1109/EEEIC/ICPSEurope51590.2021.9584526",

language = "English",

series = "21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings",

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

pages = "1--4",

editor = "Leonowicz, \{Zbigniew M.\}",

booktitle = "2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I\&CPS Europe)",

}

Wang, K, Ma, J , Man, KL, Huang, K & Huang, X 2021, Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems. in ZM Leonowicz (ed.), 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021, Bari, Italy, 7/09/21. https://doi.org/10.1109/EEEIC/ICPSEurope51590.2021.9584526

Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems. / Wang, Kangshi; Ma, Jieming ; Man, Ka Lok et al.
2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). ed. / Zbigniew M. Leonowicz. Institute of Electrical and Electronics Engineers Inc., 2021. p. 1-4 (21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings).

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

TY - GEN

T1 - Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems

AU - Wang, Kangshi

AU - Ma, Jieming

AU - Man, Ka Lok

AU - Huang, Kaizhu

AU - Huang, Xiaowei

N1 - Funding Information: This research is supported by the Natural Science Foundation of China (Grant No. 61702353,62002296), the Natural Science Foundation of Jiangsu Province (Grant No. BK20200250), the Suzhou Science and Technology Project-Key Industrial Technology Innovation (Grant No. SYG202006), Qing Lan Project of Jiangsu Province, the Key Program Special Fund of Xi’an Jiaotong-Liverpool University (XJTLU), Suzhou, China (Grant No. KSF-A-19, KSF-E-65, KSF-P-02, KSF-E-54), the XJTLU Research Development Fund (Grant No. RDF-17-02-04), and the XJTLU Postgraduate Research Scholarship (Grand No. PGRS1906004). Publisher Copyright: © 2021 IEEE

PY - 2021

Y1 - 2021

N2 - Simulations are widely used in the field of photovoltaic systems as they provide an abundant source of data for the building and training of numerical methods or artificial intelligence techniques. However, the strategies that succeed in simulation may not be victoriously transferred to the real world due to the modeling errors. In this paper, we propose a Gaussian process regression with domain randomization, which is able to bridge the 'Sim-to-Real' gap in the application of maximum power point estimation. By randomizing the parameters of the models for the training process, the Gaussian process regression models can minimize the 'Sim-to-Real' transfer cost and adapt the dynamics of the real-world environment.

AB - Simulations are widely used in the field of photovoltaic systems as they provide an abundant source of data for the building and training of numerical methods or artificial intelligence techniques. However, the strategies that succeed in simulation may not be victoriously transferred to the real world due to the modeling errors. In this paper, we propose a Gaussian process regression with domain randomization, which is able to bridge the 'Sim-to-Real' gap in the application of maximum power point estimation. By randomizing the parameters of the models for the training process, the Gaussian process regression models can minimize the 'Sim-to-Real' transfer cost and adapt the dynamics of the real-world environment.

KW - Gaussian process regression

KW - dynamics randomization

KW - maximum power point estimation

KW - photovoltaic systems

UR - https://www.scopus.com/pages/publications/85126482267

U2 - 10.1109/EEEIC/ICPSEurope51590.2021.9584526

DO - 10.1109/EEEIC/ICPSEurope51590.2021.9584526

M3 - Conference Proceeding

AN - SCOPUS:85126482267

T3 - 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings

SP - 1

EP - 4

BT - 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)

A2 - Leonowicz, Zbigniew M.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021

Y2 - 7 September 2021 through 10 September 2021

ER -

Wang K, Ma J , Man KL, Huang K, Huang X. Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems. In Leonowicz ZM, editor, 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). Institute of Electrical and Electronics Engineers Inc. 2021. p. 1-4. (21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 - Proceedings). doi: 10.1109/EEEIC/ICPSEurope51590.2021.9584526

Sim-to-Real Transfer with Domain Randomization for Maximum Power Point Estimation of Photovoltaic Systems

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this