An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant
Developments in solar technologies are making it possible to effectively exploit solar resources in several regions of Earth, including urban areas and regions with low solar irradiation intensity. Since power and heat are fundamental necessities for all users, f users, photovoltaic/thermal (PVT) te...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-03-01
|
| Series: | Energy Exploration & Exploitation |
| Online Access: | https://doi.org/10.1177/01445987241301573 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222109986390016 |
|---|---|
| author | Stefano Aneli Giuseppe M. Tina Bekkay Hajji Safae Morgoum Antonio Gagliano |
| author_facet | Stefano Aneli Giuseppe M. Tina Bekkay Hajji Safae Morgoum Antonio Gagliano |
| author_sort | Stefano Aneli |
| collection | DOAJ |
| description | Developments in solar technologies are making it possible to effectively exploit solar resources in several regions of Earth, including urban areas and regions with low solar irradiation intensity. Since power and heat are fundamental necessities for all users, f users, photovoltaic/thermal (PVT) technology has emerged as a promising solution for sustainably-minded communities. Generally, the output electrical generation of a PVT system depends on the intermittent solar insolation, efficiency, and operating temperature of the photovoltaic (PV) cell. At the same time, thermal power also depends on collector thermal insulation and the temperature difference with the surroundings. Consequently, it is essential to predict and diagnose the PVT system's power to optimally utilize the collected solar energy. In recent years, intelligent techniques and approaches have been introduced to evaluate the performance of PVT systems. Artificial Intelligence (AI)-based methods have become prominent due to their capability of producing accurate predictions against the uncertainty and nonlinearity phenomena. This work presents an innovative application of AI for both the forecasting and the diagnostic of the performance of a PVT plant. The analyses performed are based on the experimental investigation conducted on the PVT system installed at the University of Catania campus. The outcomes of this study showed that the AI accurately predicted photovoltaic energy production and consequently, it can be used to detect periods of performance loss. From the test carried out in the real plant, it was seen that the use of the AI allows for prompt identification of malfunctioning in PVT plants can translate into avoid loss of over 5% of the electricity produced, and the total loss of thermal energy. |
| format | Article |
| id | doaj-art-8ccf12d19a644ce8932f1fbb67e1e6e3 |
| institution | OA Journals |
| issn | 0144-5987 2048-4054 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Energy Exploration & Exploitation |
| spelling | doaj-art-8ccf12d19a644ce8932f1fbb67e1e6e32025-08-20T02:06:27ZengSAGE PublishingEnergy Exploration & Exploitation0144-59872048-40542025-03-014310.1177/01445987241301573An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT PlantStefano Aneli0Giuseppe M. Tina1Bekkay Hajji2Safae Morgoum3Antonio Gagliano4 , Catania, Italy , Catania, Italy , Oujda, Morocco , Oujda, Morocco , Catania, ItalyDevelopments in solar technologies are making it possible to effectively exploit solar resources in several regions of Earth, including urban areas and regions with low solar irradiation intensity. Since power and heat are fundamental necessities for all users, f users, photovoltaic/thermal (PVT) technology has emerged as a promising solution for sustainably-minded communities. Generally, the output electrical generation of a PVT system depends on the intermittent solar insolation, efficiency, and operating temperature of the photovoltaic (PV) cell. At the same time, thermal power also depends on collector thermal insulation and the temperature difference with the surroundings. Consequently, it is essential to predict and diagnose the PVT system's power to optimally utilize the collected solar energy. In recent years, intelligent techniques and approaches have been introduced to evaluate the performance of PVT systems. Artificial Intelligence (AI)-based methods have become prominent due to their capability of producing accurate predictions against the uncertainty and nonlinearity phenomena. This work presents an innovative application of AI for both the forecasting and the diagnostic of the performance of a PVT plant. The analyses performed are based on the experimental investigation conducted on the PVT system installed at the University of Catania campus. The outcomes of this study showed that the AI accurately predicted photovoltaic energy production and consequently, it can be used to detect periods of performance loss. From the test carried out in the real plant, it was seen that the use of the AI allows for prompt identification of malfunctioning in PVT plants can translate into avoid loss of over 5% of the electricity produced, and the total loss of thermal energy.https://doi.org/10.1177/01445987241301573 |
| spellingShingle | Stefano Aneli Giuseppe M. Tina Bekkay Hajji Safae Morgoum Antonio Gagliano An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant Energy Exploration & Exploitation |
| title | An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant |
| title_full | An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant |
| title_fullStr | An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant |
| title_full_unstemmed | An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant |
| title_short | An AI-Based Approach for the Assessment of the Lost Efficiencies of a PVT Plant |
| title_sort | ai based approach for the assessment of the lost efficiencies of a pvt plant |
| url | https://doi.org/10.1177/01445987241301573 |
| work_keys_str_mv | AT stefanoaneli anaibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT giuseppemtina anaibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT bekkayhajji anaibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT safaemorgoum anaibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT antoniogagliano anaibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT stefanoaneli aibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT giuseppemtina aibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT bekkayhajji aibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT safaemorgoum aibasedapproachfortheassessmentofthelostefficienciesofapvtplant AT antoniogagliano aibasedapproachfortheassessmentofthelostefficienciesofapvtplant |