Exploiting Digitalization of Solar PV Plants Using Machine Learning: Digital Twin Concept for Operation

Tolga Yalçin, Pol Paradell Solà (), Paschalia Stefanidou-Voziki, Jose Luis Domínguez-García () and Tugce Demirdelen
Additional contact information
Tolga Yalçin: Power Electronics Department, Catalonia Institut for Energy Research—IREC, Jardins de les Dones de Negre 1, 2 a pl., Sant Adrià del Besòs, 08930 Barcelona, Spain
Pol Paradell Solà: Power Electronics Department, Catalonia Institut for Energy Research—IREC, Jardins de les Dones de Negre 1, 2 a pl., Sant Adrià del Besòs, 08930 Barcelona, Spain
Paschalia Stefanidou-Voziki: E.ON Digital Technology GmbH, Georg-Brauchle-Ring 52-54, 80992 Munich, Germany
Jose Luis Domínguez-García: Power Electronics Department, Catalonia Institut for Energy Research—IREC, Jardins de les Dones de Negre 1, 2 a pl., Sant Adrià del Besòs, 08930 Barcelona, Spain
Tugce Demirdelen: Departmentof Electrical and Electronics Engineering, Alparslan Turkes Science and Technology University—ATU, Balcalı Mah., South Campus 10 Street, No:1U, P.O. Box GP 561 Adana, Turkey

Energies, 2023, vol. 16, issue 13, 1-17

Abstract: The rapid development of digital technologies and solutions is disrupting the energy sector. In this regard, digitalization is a facilitator and enabler for integrating renewable energies, management and operation. Among these, advanced monitoring techniques and artificial intelligence may be applied in solar PV plants to improve their operation and efficiency and detect potential malfunctions at an early stage. This paper proposes a Digital Twin DT concept, mainly focused on O&M, to obtain more information about the system by using several artificial intelligence boxes. Furthermore, it includes the development of several machine learning (ML) algorithms capable of reproducing the expected behavior of the solar PV plant and detecting the malfunctioning of different components. In this regard, this allows for reducing downtime and optimizing asset management. In this paper, different ML techniques are used and compared to optimize the selected methods for enhanced response. The paper presents all stages of the developed Digital Twin, including ML model development with an accuracy of 98.3% of the whole DT, and finally, a communication and visualization platform. The different responses and comparisons have been made using a model based on MATLAB/Simulink using different cases and system conditions.

Keywords: Digital Twin; PV system; solar plant; machine learning; O&M systems (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/13/5044/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/13/5044/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:13:p:5044-:d:1182667

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().