On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning
Building integrated photovoltaic (BIPV), based on tandem PV cells, is considered a new alternative for combining solar energy with buildings. Accurately predicting the BIPV-harvested annual output energy (Eout,annual) is crucial for evaluating the BIPV performance. Machine learning (ML) is a potenti...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023053057 |
| _version_ | 1797771464227684352 |
|---|---|
| author | Dong C. Nguyen Yasuaki Ishikawa |
| author_facet | Dong C. Nguyen Yasuaki Ishikawa |
| author_sort | Dong C. Nguyen |
| collection | DOAJ |
| description | Building integrated photovoltaic (BIPV), based on tandem PV cells, is considered a new alternative for combining solar energy with buildings. Accurately predicting the BIPV-harvested annual output energy (Eout,annual) is crucial for evaluating the BIPV performance. Machine learning (ML) is a potential candidate for solving such a problem without the time-consuming process of experimental investigations. This contribution proposes an artificial neural network (ANN) to predict the Eout,annual of 4-terminal perovskite/silicon (psk/Si) PV cells under realistic environmental conditions. The input variables of the proposed model consist of the input solar irradiance (Pin), incident light's angle (Ain), the PV module's temperature (Tmod), the psk absorber's thickness (Thpsk), and the psk absorber's bandgap (Bpsk). The input data were received from the simulated results. This work also evaluates the degree of importance of each input variable and optimizes the architecture of the ANN using the surrogate algorithm before predictions. The optimized ANN-3 (three hidden layers) model shows superior performance indicators, including a mean squared error of MSE = 0.02283, correlation coefficient R = 0.99999, and Willmott's index of agreement Iw = 0.99999. Consequently, the predicted highest Eout,annual at Bpsk of 1.71 eV is 297.73, 115.01, 193.98, and 97.6 kWh/m2 for the rooftop, east, south, and west facades, respectively. |
| first_indexed | 2024-03-12T21:37:57Z |
| format | Article |
| id | doaj.art-eb4f085839584f4cb1260c0321461bd1 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-12T21:37:57Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-eb4f085839584f4cb1260c0321461bd12023-07-27T05:58:32ZengElsevierHeliyon2405-84402023-07-0197e18097On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learningDong C. Nguyen0Yasuaki Ishikawa1College of Science and Engineering, Aoyama Gakuin University, Sagamihara, Kanagawa 252-5258, Japan; Institute of Materials Science, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay, Hanoi 100000, Viet Nam; Corresponding authors at: College of Science and Engineering, Aoyama Gakuin University, Sagamihara, Kanagawa 252-5258, Japan.College of Science and Engineering, Aoyama Gakuin University, Sagamihara, Kanagawa 252-5258, Japan; Corresponding authors at: College of Science and Engineering, Aoyama Gakuin University, Sagamihara, Kanagawa 252-5258, Japan.Building integrated photovoltaic (BIPV), based on tandem PV cells, is considered a new alternative for combining solar energy with buildings. Accurately predicting the BIPV-harvested annual output energy (Eout,annual) is crucial for evaluating the BIPV performance. Machine learning (ML) is a potential candidate for solving such a problem without the time-consuming process of experimental investigations. This contribution proposes an artificial neural network (ANN) to predict the Eout,annual of 4-terminal perovskite/silicon (psk/Si) PV cells under realistic environmental conditions. The input variables of the proposed model consist of the input solar irradiance (Pin), incident light's angle (Ain), the PV module's temperature (Tmod), the psk absorber's thickness (Thpsk), and the psk absorber's bandgap (Bpsk). The input data were received from the simulated results. This work also evaluates the degree of importance of each input variable and optimizes the architecture of the ANN using the surrogate algorithm before predictions. The optimized ANN-3 (three hidden layers) model shows superior performance indicators, including a mean squared error of MSE = 0.02283, correlation coefficient R = 0.99999, and Willmott's index of agreement Iw = 0.99999. Consequently, the predicted highest Eout,annual at Bpsk of 1.71 eV is 297.73, 115.01, 193.98, and 97.6 kWh/m2 for the rooftop, east, south, and west facades, respectively.http://www.sciencedirect.com/science/article/pii/S2405844023053057Building integrated photovoltaicTandem PV cellAtlas simulationMachine learningPhotovoltaicSurrogate algorithm |
| spellingShingle | Dong C. Nguyen Yasuaki Ishikawa On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning Heliyon Building integrated photovoltaic Tandem PV cell Atlas simulation Machine learning Photovoltaic Surrogate algorithm |
| title | On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning |
| title_full | On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning |
| title_fullStr | On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning |
| title_full_unstemmed | On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning |
| title_short | On predicting annual output energy of 4-terminal perovskite/silicon tandem PV cells for building integrated photovoltaic application using machine learning |
| title_sort | on predicting annual output energy of 4 terminal perovskite silicon tandem pv cells for building integrated photovoltaic application using machine learning |
| topic | Building integrated photovoltaic Tandem PV cell Atlas simulation Machine learning Photovoltaic Surrogate algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023053057 |
| work_keys_str_mv | AT dongcnguyen onpredictingannualoutputenergyof4terminalperovskitesilicontandempvcellsforbuildingintegratedphotovoltaicapplicationusingmachinelearning AT yasuakiishikawa onpredictingannualoutputenergyof4terminalperovskitesilicontandempvcellsforbuildingintegratedphotovoltaicapplicationusingmachinelearning |