Predicting Module Performance from Cell and Module Parameters Using Machine Learning

Marco Ernst; Hannes Wagner-Mohnsen; Sven Wasmer; Bernhard Klöter; Pietro P. Altermatt

doi:10.1364/IPRSN.2023.JW2E.5

Predicting Module Performance from Cell and Module Parameters Using Machine Learning

Marco Ernst
, Hannes Wagner-Mohnsen
, Sven Wasmer
, Bernhard Klöter
, Pietro P. Altermatt

Research output: Contribution to conference › Paper › peer-review

Abstract

We use machine learning and device physics to analyze mass-produced solar modules, identifying factors that affect performance. Our approach is demonstrated by simulating 10,000 PERC solar cells and 2,000 half-cell modules using numerical device simulations. Our flexible approach can be applied to real data from production lines and scenarios.

Original language	English
Number of pages	3
DOIs	https://doi.org/10.1364/IPRSN.2023.JW2E.5
Publication status	Published - 2023
Event	2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023 - Busan, Korea, Republic of Duration: 9 Jul 2023 → 13 Jul 2023

Conference

Conference	2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023
Country/Territory	Korea, Republic of
City	Busan
Period	9/07/23 → 13/07/23

Access to Document

10.1364/IPRSN.2023.JW2E.5

Cite this

Ernst, M., Wagner-Mohnsen, H., Wasmer, S., Klöter, B., & Altermatt, P. P. (2023). Predicting Module Performance from Cell and Module Parameters Using Machine Learning. Paper presented at 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023, Busan, Korea, Republic of. https://doi.org/10.1364/IPRSN.2023.JW2E.5

@conference{4f082f58616d4e41a1e388aab1d02d97,

title = "Predicting Module Performance from Cell and Module Parameters Using Machine Learning",

abstract = "We use machine learning and device physics to analyze mass-produced solar modules, identifying factors that affect performance. Our approach is demonstrated by simulating 10,000 PERC solar cells and 2,000 half-cell modules using numerical device simulations. Our flexible approach can be applied to real data from production lines and scenarios.",

author = "Marco Ernst and Hannes Wagner-Mohnsen and Sven Wasmer and Bernhard Kl{\"o}ter and Altermatt, \{Pietro P.\}",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2023 {\textcopyright} 2023 The Author(s).; 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023 ; Conference date: 09-07-2023 Through 13-07-2023",

year = "2023",

doi = "10.1364/IPRSN.2023.JW2E.5",

language = "English",

}

Ernst, M, Wagner-Mohnsen, H, Wasmer, S, Klöter, B & Altermatt, PP 2023, 'Predicting Module Performance from Cell and Module Parameters Using Machine Learning', Paper presented at 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023, Busan, Korea, Republic of, 9/07/23 - 13/07/23. https://doi.org/10.1364/IPRSN.2023.JW2E.5

Predicting Module Performance from Cell and Module Parameters Using Machine Learning. / Ernst, Marco; Wagner-Mohnsen, Hannes; Wasmer, Sven et al.
2023. Paper presented at 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023, Busan, Korea, Republic of.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Predicting Module Performance from Cell and Module Parameters Using Machine Learning

AU - Ernst, Marco

AU - Wagner-Mohnsen, Hannes

AU - Wasmer, Sven

AU - Klöter, Bernhard

AU - Altermatt, Pietro P.

PY - 2023

Y1 - 2023

N2 - We use machine learning and device physics to analyze mass-produced solar modules, identifying factors that affect performance. Our approach is demonstrated by simulating 10,000 PERC solar cells and 2,000 half-cell modules using numerical device simulations. Our flexible approach can be applied to real data from production lines and scenarios.

AB - We use machine learning and device physics to analyze mass-produced solar modules, identifying factors that affect performance. Our approach is demonstrated by simulating 10,000 PERC solar cells and 2,000 half-cell modules using numerical device simulations. Our flexible approach can be applied to real data from production lines and scenarios.

UR - https://www.scopus.com/pages/publications/85192396631

UR - https://opg.optica.org/abstract.cfm?uri=SPPCom-2023-JW2E.5

U2 - 10.1364/IPRSN.2023.JW2E.5

DO - 10.1364/IPRSN.2023.JW2E.5

M3 - Paper

AN - SCOPUS:85192396631

T2 - 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023

Y2 - 9 July 2023 through 13 July 2023

ER -

Ernst M, Wagner-Mohnsen H, Wasmer S, Klöter B, Altermatt PP. Predicting Module Performance from Cell and Module Parameters Using Machine Learning. 2023. Paper presented at 2023 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2023 in Advanced Photonics Congress - Part of Advanced Photonics Congress 2023, Busan, Korea, Republic of. doi: 10.1364/IPRSN.2023.JW2E.5

Predicting Module Performance from Cell and Module Parameters Using Machine Learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this