Neural Network Modeling of the Solar Photovoltaic Thermal Module Performance

  • Наталья [Natalya] Сергеевна [S.] Филиппченкова [Filippchenkova]
Keywords: solar module, solar collector, photovoltaic module, photovoltaic thermal module, thermal efficiency, electric efficiency, feedforward artificial neural network, training algorithm

Abstract

The design of photovoltaic thermal modules (PVT modules) features a nonuniform distribution of coolant temperature in the channel, and the solar cells (SC) that are in thermal contact with the PVT module channel are under different temperature conditions. The nonuniform distribution of the SC temperature causes undesirable effects that are complex and nonlinear, such as a drop of generated power and SC damage resulting from the occurrence of hot spots. The aim of the work is to develop a mathematical model for modeling the PVT module thermal and electrical performance based on a feedforward artificial neural network (FNN). A two-layer FNN with sigmoid hidden neurons and linear output neurons has been developed. The input layer is made up of the ambient temperature, coolant flowrate and environmental variables (the total insolation). The output layer represents the PVT module thermal and electrical efficiencies. The developed FNN was trained and adapted on the basis of modeling and an experimental database on the PVT module input and output parameters. The developed FNN was trained using the Levenberg–Marquardt algorithm. The mean absolute error achieved during the training is in the range from –0.319 to 0.448 for electrical efficiency and from –0.129 to 0.198 for thermal efficiency. The r.m.s error is 0.0678 for electrical efficiency and 0.0247 for thermal efficiency; the training time is 15 s or longer. An effective model has been developed that implements a new approach to modeling the performance of PVT modules based on artificial neural network algorithms with fairly close values of thermal and electrical efficiencies.

Information about author

Наталья [Natalya] Сергеевна [S.] Филиппченкова [Filippchenkova]

Ph.D. (Techn.), Leading Design Engineer, JSC «United Energy Company», e-mail: natalja.filippchenkowa@yandex.ru

References

1. Турсунов М.Н., Дыскин В.Г., Турдиев Б.М., Юлдашев И.А. Влияние конвективного теплообмена на температуру солнечной фотоэлектрической батареи // Гелиотехника. 2014. № 4. С. 13—16.
2. Майоров В.А. Исследования тепловых характеристик теплофотоэлектрического солнечного модуля с концентратором и приемником треугольного профиля // Гелиотехника. 2018. № 6. С. 45—55.
3. Guo J., Zheng L. Numerically Study on a New Hybrid Photovoltaic Thermal (PVT) Collectors with Natural Circulation // Appl. Solar Energy. 2017. V. 53. Pp. 316—321.
4. Kazanci O.B., Skrupskelis M., Sevela P., Pavlov G.K. Olesen B.W. Sustainable Heating, Cooling and Ventilation of a Plus-energy House Via Photovoltaic/Thermal Panels // Energy Buildings. 2014. V. 83. Pp. 122—129.
5. Haloui H., Touafek K., Zaabat M., Cheikh El Hocine H.B., Khelifa A. Modelling of a Hybrid Photovoltaic Thermal Collector Based on CdTe // Appl. Solar Energy. 2016. V. 52(1). Pp. 27—31.
6. Makki A. Advancements in Hybrid Photovoltaic Systems for Enhanced Solar Cells Performance // Renew. Sust. Energy Rev. 2015. V. 41. Pp. 658—684.
7. Durrani S.P., Balluff S., Wurzer L., Krauter S. Photovoltaic Yield Prediction Using an Irradiance Forecast Model Based on Multiple Neural Networks // J. Modern Power Systems and Clean Energy. 2018. V. 6(2). Pp. 255—267.
8. Adhitya R.Y., Sarena S.T., Atmoko R.A., Hartono D. Smart PV Solar Tracking System Menggunakan Metode BP-NN (Back Propagation Neural Network) // Seminar MASTER PPNS. 2016. V. 1. Pp. 1—5.
9. Yu K.N., Yau H.T., Li J.Y. Chaotic Extension Neural Network-based Fault Diagnosis Method for Solar Photovoltaic Systems // Math. Problems in Eng. 2014. V. 2014. Pp. 1—9.
10. Abuşka M., Akgül M.B., Altıntaş V. Artificial Neural Network Modeling of the Thermal Performance of a Novel Solar Air Absorber Plate // Proc. III Rostocker Symp. Thermophys. Properties Techn. Thermodynamics. 2014. Pp. 572—581.
11. Панченко В.А. Солнечные кровельные панели для электро- и теплогенерации // Гелиотехника. 2018. № 4. C. 54—59.
12. Тихонов П.В. Обоснование параметров фотоэлектрического теплового модуля: дис. … канд. техн. наук. М.: ФБГНУ ВИЭСХ, 2014.
13. Пат. № 2546332 РФ. Гибридный фотоэлектрический модуль / Д.С. Стребков, А.Е. Иродионов, И.С. Персиц, Н.С. Филиппченкова // Бюл. изобрет. 2015. № 10.
14. Хайкин С. Преимущества и ограничения обучения методом обратного распространения. М.: Вильямс, 2006.
15. Пархоменко С.С., Леденева Т.М. Обучение нейронных сетей методом Левенберга–Марквардта в условиях большого количества данных // Вестник Воронежского гос. ун-та. Серия «Системный анализ и информационные технологии». 2014. № 2. С. 98—106.
16. Филиппченкова Н.С., Харченко А.В. Разработка автоматической системы регистрации основных параметров солнечной концентраторной установки // Фундаментальные и прикладные вопросы физики: Труды Междунар. конф. Ташкент: Изд-во АН Республики Узбекистан НПО «Физика-Солнце», 2017. C. 192—195.
---
Для цитирования: Филиппченкова Н.С. Нейросетевое моделирование производительности солнечного теплофотоэлектрического модуля // Вестник МЭИ. 2022. № 2. С. 56—62. DOI: 10.24160/1993-6982-2022-2-56-62.
#
1. Tursunov M.N., Dyskin V.G., Turdiev B.M., Yuldashev I.A. Vliyanie Konvektivnogo Teploobmena na Temperaturu Solnechnoy Fotoelektricheskoy Batarei. Geliotekhnika. 2014;4:13—16. (in Russian).
2. Mayorov V.A. Issledovaniya Teplovykh Kharakteristik Teplofotoelektricheskogo Solnechnogo Modulya s Kontsentratorom i Priemnikom Treugol'nogo Profilya. Geliotekhnika. 2018;6:45—55. (in Russian).
3. Guo J., Zheng L. Numerically Study on a New Hybrid Photovoltaic Thermal (PVT) Collectors with Natural Circulation. Appl. Solar Energy. 2017;53:316—321.
4. Kazanci O.B., Skrupskelis M., Sevela P., Pavlov G.K. Olesen B.W. Sustainable Heating, Cooling and Ventilation of a Plus-energy House Via Photovoltaic/Thermal Panels. Energy Buildings. 2014;83:122—129.
5. Haloui H., Touafek K., Zaabat M., Cheikh El Hocine H.B., Khelifa A. Modelling of a Hybrid Photovoltaic Thermal Collector Based on CdTe. Appl. Solar Energy. 2016;52(1):27—31.
6. Makki A. Advancements in Hybrid Photovoltaic Systems for Enhanced Solar Cells Performance. Renew. Sust. Energy Rev. 2015;41:658—684.
7. Durrani S.P., Balluff S., Wurzer L., Krauter S. Photovoltaic Yield Prediction Using an Irradiance Forecast Model Based on Multiple Neural Networks. J. Modern Power Systems and Clean Energy. 2018;6(2):255—267.
8. Adhitya R.Y., Sarena S.T., Atmoko R.A., Hartono D. Smart PV Solar Tracking System Menggunakan Metode BP-NN (Back Propagation Neural Network). Seminar MASTER PPNS. 2016;1:1—5.
9. Yu K.N., Yau H.T., Li J.Y. Chaotic Extension Neural Network-based Fault Diagnosis Method for Solar Photovoltaic Systems. Math. Problems in Eng. 2014;2014:1—9.
10. Abuşka M., Akgül M.B., Altıntaş V. Artificial Neural Network Modeling of the Thermal Performance of a Novel Solar Air Absorber Plate. Proc. III Rostocker Symp. Thermophys. Properties Techn. Thermodynamics. 2014:572—581.
11. Panchenko V.A. Solnechnye Krovel'nye Paneli dlya Elektro- i Teplogeneratsii. Geliotekhnika. 2018;4:54—59. (in Russian).
12. Tikhonov P.V. Obosnovanie Parametrov Fotoelektricheskogo Teplovogo Modulya: Dis. … Kand. Tekhn. Nauk. M.: FBGNU VIESKH, 2014. (in Russian).
13. Pat № 2546332 RF. Gibridnyy Fotoelektricheskiy Modul'. D.S. Strebkov, A.E. Irodionov, I.S. Persits, N.S. Filippchenkova. Byul. izobret. 2015;10. (in Russian).
14. Khaykin S. Preimushchestva i Ogranicheniya Obucheniya Metodom Obratnogo Rasprostraneniya. M.: Vil'yams, 2006. (in Russian).
15. Parkhomenko S.S., Ledeneva T.M. Obuchenie Neyronnykh Setey Metodom Levenberga–Markvardta v Usloviyakh Bol'shogo Kolichestva Dannykh. Vestnik Voronezhskogo Gos. Un-Ta. Seriya «Sistemnyy Analiz i Informatsionnye Tekhnologii». 2014;2:98—106. (in Russian).
16. Filippchenkova N.S., Kharchenko A.V. Razrabotka Avtomaticheskoy Sistemy Registratsii Osnovnykh Parametrov Solnechnoy Kontsentratornoy Ustanovki. Fundamental'nye i Prikladnye Voprosy Fiziki: Trudy Mezhdunar. Konf. Tashkent: Izd-vo AN Respubliki Uzbekistan NPO «Fizika-Solntse», 2017:192—195. (in Russian).
---
For citation: Filippchenkova N.S. Neural Network Modeling of the Solar Photovoltaic Thermal Module Performance. Bulletin of MPEI. 2022;2:56—62. (in Russian). DOI: 10.24160/1993-6982-2022-2-56-62.
Published
2021-08-09
Section
Renewable Energy Installations (05.14.08)