Raqamli Transformatsiya va Sun’iy Intellekt
MASHINAVIY O‘QITISHGA ASOSLANGAN GIBRID MODELLI INTELLEKTUAL TAVSIYA TIZIMI YORDAMIDA O‘ZBEKISTON HUDUDIDA QAYTA TIKLANUVCHI ENERGIYA OBYEKTLARI JOYLASHUVINI ANIQLASHDA O‘ZARO MOSLIK KO‘RSATKICHLARINING AHAMIYATI
1 t.f.d professor Televizion texnologiyalar fakulteti dekani Muhamad al Xorazmiy nomidagi Toshkent axborot texnologiyalar universiteti
2 Phd tayanch doktorant Tashkent shaxridagi Belarus-O’zbekiston qo’shma tarmoqlar aro amaliy texnik kvalifikatsiya Insttituti
Zenodo DOI: 10.5281/zenodo.19696314
Keywords
Abstract
Ushbu maqolada O‘zbekiston hududida qayta tiklanuvchi energiya manbalari asosidagi elektr energiyasi ishlab chiqarish obyektlarini joylashtirish uchun mashinaviy o‘qitishga asoslangan gibrid modelli intellektual tavsiya tizimini ishlab chiqish masalasi ko‘rib chiqiladi. Tadqiqot doirasida NASA POWER ochiq ma’lumotlari asosida hudud bo‘yicha panjara (grid) nuqtalar shaklida quyosh radiatsiyasi, to‘g‘ridan-to‘g‘ri nurlanish, shamol tezligi va havo harorati ko‘rsatkichlaridan iborat iqlimiy dataset shakllantirildi. Olingan ma’lumotlar normalizatsiya qilinib, quyosh energiyasi, shamol energiyasi hamda ularning kombinatsiyasini ifodalovchi gibrid moslik ko‘rsatkichlari hisoblandi. Gibrid moslik qiymatlarini bashoratlash va tahlil qilish uchun Random Forest va XGBoost algoritmlariga asoslangan regressiya modellari qurildi. Modellarning samaradorligi determinatsiya koeffitsienti (R²) va o‘rtacha absolyut xato (MAE) mezonlari asosida baholandi. Tajriba natijalari gibrid moslikni shakllantirishda harorat va shamol tezligi omillarining muhim ahamiyatga ega ekanligini ko‘rsatdi. Shuningdek, ishlab chiqilgan tavsiya tizimi yordamida O‘zbekiston hududi bo‘yicha eng istiqbolli hududlar aniqlanib, ularning fazoviy taqsimoti interaktiv xarita ko‘rinishida vizualizatsiya qilindi. Tadqiqot natijalari qayta tiklanuvchi energiya obyektlarini optimal joylashtirish bo‘yicha qaror qabul qilish jarayonlarini qo‘llab-quvvatlash hamda energetika sohasida raqamli transformatsiyani jadallashtirishga xizmat qiladi.
References
- Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD Conference. – 2016. – P. 785–794.
- Shahriari M., Blumsack S. GIS-based spatial analysis of renewable energy potential // Applied Energy. – 2018. – Vol. 209. – P. 379–393.
- Foley A.M., Leahy P.G., Li K. A long-term analysis of wind power potential in Ireland // Renewable Energy. – 2012. – Vol. 38, No.1. – P. 1–11.
- Hong T., Wang P., White L. Weather data preprocessing for predicting building energy consumption using machine learning techniques // Energy and Buildings. – 2015. – Vol. 86. – P. 617–627.
- Li X., Cheng C., Li Y. GIS-based assessment of wind and solar energy potential in China // Energy. – 2019. – Vol. 174. – P. 926–937.
- Goodfellow I., Bengio Y., Courville A. Deep learning. – MIT Press, 2016. – 775 p.
- Zhang Y., Wang J., Wang X. Review on probabilistic forecasting of wind power generation // Renewable and Sustainable Energy Reviews. – 2014. – Vol. 32. – P. 255–270.
- Janke J.R. Multicriteria GIS modeling of wind and solar farms in Colorado // Renewable Energy. – 2010. – Vol. 35, No.10. – P. 2228–2234.
- Bhattacharyya S.C. Energy economics: Concepts, issues, markets and governance. – Springer, 2019. – 410 p.
- Wang J., Wang X. Machine learning models for predicting renewable energy generation: A review // Renewable and Sustainable Energy Reviews. – 2020. – Vol. 119. – P. 109596.
- NASA Prediction of Worldwide Energy Resources (POWER) Project. – 2024. – URL: https://power.larc.nasa.gov
- Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45, No.1. – P. 5–32.
- Hastie T., Tibshirani R., Friedman J. The elements of statistical learning: Data mining, inference, and prediction. – 2nd ed. – Springer, 2009. – 745 p.
- Gielen D., Boshell F., Saygin D. The role of renewable energy in the global energy transformation // Energy Strategy Reviews. – 2019. – Vol. 24. – P. 38–50.
- Alizamir M., Kim S., Zohrevand M. A hybrid machine learning approach for renewable energy site selection // Energy Reports. – 2021. – Vol. 7. – P. 5436–5449.
- Lund H., Østergaard P.A., Connolly D. Smart energy and smart energy systems // Energy. – 2017. – Vol. 137. – P. 556–565.
- Ahmad T., Zhang D., Huang C. Artificial intelligence in sustainable energy industry: Status quo, challenges and opportunities // Journal of Cleaner Production. – 2020. – Vol. 289. – P. 125834.