PVLIB ASOSIDA KICHIK QUVVATLI QUYOSH FOTOELEKTRIK STANSIYASINING QISQA MUDDATLI QUVVAT PROGNOZI

Admin bo'lib kirish (www.admin.slib.uz)

Tizim sinov (TEST) rejimida ishlamoqda! Murojat uchun @slib_support

Eski talqinga o'tish link

20 август 2025

Asosiy til:O'zbek

PVLIB ASOSIDA KICHIK QUVVATLI QUYOSH FOTOELEKTRIK STANSIYASINING QISQA MUDDATLI QUVVAT PROGNOZI

Fan yo'nalishi:

68a7e0962ecd5.pdf

PDF

MUQOBIL ENERGETIKA

Maqola chop etish see more

MAQOLA ANNOTATSIYASI

Annotatsiya. Kirish.Ushbu tadqiqotda Toshkent shahridagi 9 kW quvvatga ega tom usti quyosh fotoelektrik stansiyaning qisqa muddatli quvvat prognozi modeli ishlab chiqildi. Model PVlib Python kutubxonasi yordamida fizik asosda qurilib, ICON Global ob-havo parametrlari (GHI, DNI, DHI, havo harorati, shamol tezligi) sun’iy neyron tarmoq (LSTM+CNN) orqali yer usti o‘lchovlari bilan kalibrlandi. Model oniy quvvat bo‘yicha R² = 0,87 (MAE = 535 W), soatlik energiya bo‘yicha esa R² = 0,95 (MAE = 0,37 kWh) aniqlikka erishdi. Arzon va ishonchli elektr energiyasiga bo‘lgan ehtiyoj iqtisodiy va ijtimoiy rivojlanish uchun muhim omil sanaladi. Quyosh fotoelektrik stansiyalar respublikada qayta tiklanuvchi energiya ulushini oshirishda yetakchi rol o‘ynaydi, biroq ularning ishlab chiqarishi ob-havo sharoitlarining o‘zgaruvchanligiga bog‘liq. Shu bois qisqa muddatli prognozlash usullari ishlab chiqarish va tarmoqni boshqarish samaradorligini oshirishda muhim ahamiyat kasb etadi. Materiallar va usullar. Tadqiqot obyekti sifatida Toshkentdagi 9 kW quvvatga ega tom usti fotoelektrik stansiya tanlandi. Tizim 39 dona 250 W Luxco panellar va Deye SUN-10K-G invertordan iborat bo‘lib, janubi-sharq (azimut 167,2°) yo‘nalishda, 33° burchak ostida oʻrnatilgan. Meteorologik maʼlumotlar uchun Germaniyaning DWD tomonidan ishlab chiqilgan ICON Global NWP modeli natijalari (GHI, DNI, DHI, havo harorati, shamol tezligi) asos qilib olindi. Model fizik yondashuv uchun PVlib kutubxonasidan foydalanadi, yaʼni quyosh radiatsiyasi va tizim parametrlarini fizik qonuniyatlarga muvofiq modellashtiradi. Keyin ANN (LSTM+CNN) yordamida ICON parametrlarining lokal xatoliklari yer usti o‘lchovlari bilan kalibrlanadi. Model P(t) oniy quvvat (W) va E soatlik energiya (kWh) prognozlarini beradi. Natijalar MAE, MAPE va R² statistik koʻrsatkichlari asosida baholandi hamda grafik va tarqalish diagrammalari yordamida vizual tahlil qilindi. Natijalar. Oniy quvvat (P): Model-haqiqiy qiymatlar orasidagi korrelyatsiya R² = 0,87, MAE = 535 W. Soatlik energiya (E): R² = 0,95, MAE = 0,37 kWh. Xulosa. Gibrid PVlib + ANN yondashuvi 9 kW stansiya uchun qisqa muddatli prognozda R² ≥ 0,87 va past MAE (535 W, 0,37 kWh) ko‘rsatkichlarini berdi. Model tarmoq boshqaruvi va energiya rejalashtirishda amaliy yordamchi vosita ekanini isbotladi. Kelajakda mavsumiy kengaytmalar va ilg‘or usullar integratsiyasi rejalashtiriladi.

MUALIFLAR

Teglar

# photovoltaic station# фотоэлектрическая станция# LSTM# CNN# Fotoelektrik stansiya# ICON Global# PVlib# ANN# IEA

Maqolani baholang

0

0 ta

Maqola idintifikatorlari

ROI:

https://eroi.uz/11.0032/A0825-0014

DOI:

Mavjud emas

Foydalanilgan adabiyotlar

[1] United Nations. (2023). Tracking SDG7: The Energy Progress Report. https://www.iea.org/reports/tracking-sdg7-the-energy-progress-report-2023.

[2] IEA. (2022). World Energy Outlook 2022. https://www.iea.org/reports/world-energy-outlook-2022.

[4] International Renewable Energy Agency (IRENA). (2024). Renewable Energy Statistics 2024. Abu Dhabi: IRENA. Retrieved from https://www.irena.org/publications

[5] Ministry of Energy of the Republic of Uzbekistan. (2023). National energy development targets.

[6] International Renewable Energy Agency (IRENA). (2023). Uzbekistan: Renewable energy country profile and statistics. Abu Dhabi: IRENA. Retrieved from https://www.irena.org/Statistics/View-Data-by-Country

[7] International Energy Agency (IEA). (2024). Uzbekistan Power Sector Overview. Paris: International Energy Agency. Retrieved from https://www.iea.org/reports/uzbekistan-power-sector-overview

[8] Raximov E.Yu., Omonov B.Yu., Imyaminov A.A. (2024). Oʻzbekiston hududlari uchun kunlik yigʻindi quyosh radiatsiyasi qiymatini aniqlashda xalqaro bazalardan foydalanish imkoniyati. Yarim oʻtkazgichlar instituti tezislari toʻplami, IV Respublika ilmiy anjumani materiali, 237–240.

[9] Pedro H. T. C., & Coimbra C. F. M. (2012). Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy, 86(7), 2017–2028. https://doi.org/10.1016/j.solener.2012.04.004

[10] Qazi M. A., Khan M. A., Rehman A. U., Iqbal, W., & Zahid, M. (2020). Short-term photovoltaic power forecasting using an LSTM network and historical weather data. Energies, 13(14), 3653. https://doi.org/10.3390/en13143653

[11] Shi X., Chen Z., Wang H., Yeung D.Y., Wong W.K., & Woo W.C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems (Vol. 28). https://papers.nips.cc/paper_files/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.html

[12] https://www.dwd.de/EN/ourservices/nwp_forecast_data/nwp_forecast_data.htm l?utm_source=chatgpt.com

[13] Zängl G., Reinert D., Rípodas P., & Baldauf M. (2015). The ICON modelling framework. QJRMS, 141(687), 563–579. https://doi.org/10.1002/qj.2378

[14] Stüber M., Scherhag F., Deru M., Ndiaye A., Sakha M. M., Brandherm B., Baus J., & Frey G. (2021). Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System. Frontiers in Energy Research, 9, 639346. https://doi.org/10.3389/fenrg.2021.639346

[15] Pedro H.T.C., & Coimbra C.F.M. (2012). Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy, 86(7), 2017–2028. https://doi.org/10.1016/j.solener.2012.04.004

[16] PVlib python: Simulating solar energy systems. Retrieved from https://pvlib-python.readthedocs.io/en/stable/gallery/index.html

[17] Holmgren W.F., Hansen C.W., & Mikofski M. A. (2018). PVlib Python: A Python package for modeling solar energy systems. Journal of Open Source Software, 3(29), 884. https://doi.org/10.21105/joss.00884

[18] Zängl G., Reinert D., Rípodas P., & Baldauf M. (2015). The ICON modelling framework of DWD and MPI-M: Description of the nonhydrostatic dynamical core. Quarterly Journal of the Royal Meteorological Society, 141(687), 563–579. https://doi.org/10.1002/qj.2378

[19] Mandal P., Senjyu T., Yona A., Saber A.Y., & Funabashi, T. (2012). A novel approach to forecast solar irradiance using neural network. Energy Conversion and Management, 52(1), 361–368. https://doi.org/10.1016/j.enconman.2010.07.032

[20] Voyant C., Notton G., Kalogirou S., Nivet M.L., Paoli C., Motte F., & Fouilloy A. (2017). Machine learning methods for solar radiation forecasting: A review. Renewable Energy, 105, 569–582. https://doi.org/10.1016/j.renene.2016.12.095

[21] Antonanzas J., Osorio N., Escobar R., Urraca R., de Pison F. M., & Antonanzas-Torres F. (2016). Review of photovoltaic power forecasting. Solar Energy, 136, 78–111. https://doi.org/10.1016/j.solener.2016.06.069

[22] Raximov E.Yu., Imyaminov A.A., & Jamoldinov F.Z. (2023). Quyosh fotoelektrik tizimlari ishlab chiqarish quvvatini bashoratlash usullari. In Qishloq xoʻjaligida resurs tejamkor innovatsion texnologiyalardan samarali foydalanishning ilmiy-amaliy asoslari: Xalqaro ilmiy-texnik anjuman maqolalari toʻplami, II qism (bet. 648–652). Andijon: AQXATI.

[3] International Renewable Energy Agency (IRENA). (2024). Renewable Energy Statistics 2024. Abu Dhabi: IRENA. Retrieved from https://www.irena.org/publications