Том 337 № 1 (2026)
DOI https://doi.org/10.18799/24131830/2026/1/4965
Новый гибридный подход к моделированию для улучшенного прогнозирования солнечной энергетики
Возобновляемые энергетические ресурсы становятся все более важными для устойчивого производства энергии, но точное прогнозирование их выработки остается сложной задачей из-за нестабильных данных и колеблющихся экологических условий. В этом исследовании представлен новый гибридный модельный подход, сочетающий вариационную модальную декомпозицию с передовыми методами прогнозирования для повышения точности и надежности прогнозов солнечной энергетики. Оценка данных от двух подключенных к сети солнечных электростанций в Алжире показала значительные улучшения по сравнению с традиционными методами, включая Long Short-Term Memory, 1D-Convolutional Neural Network и Gated Recurrent Unit. Ключевые результаты показали значительное сокращение корня из средней квадратичной ошибки до 89,39 %, что подчеркивает эффективность предложенного подхода.
Ключевые слова:
возобновляемые энергетические ресурсы, прогнозирование, нестабильные данные, вариационная модальная декомпозиция, прогнозирование солнечной энергии, подключенные к сети солнечные электростанции, Long Short-Term Memory
Библиографические ссылки:
REFERENCES
1. Rabehi A., Guermoui M., Lalmi D. Hybrid models for global solar radiation prediction: a case study. International Journal of Ambient Energy, 2020, vol. 41 (1), pp. 31–40.
2. Guermoui Mawloud. An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques. Scientific Reports, 2024, vol. 14.1, 6653.
3. Guermoui Mawloudl. Enhancing direct normal solar irradiation forecasting for heliostat field applications through a novel hybrid model. Energy Conversion and Management, 2024, vol. 304, 118189.
4. Gupta Priya, Rhythm Singh. PV power forecasting based on data-driven models: a review. International Journal of Sustainable Engineering, 2021, vol. 14.6, pp. 1733–1755.
5. Guermoui Mawloud. Forecasting intra-hour variance of photovoltaic power using a new integrated model. Energy Conversion and Management, 2021, vol. 245, 114569.
6. Belaid A., Guermoui M., Khelifi R., Arrif T., Chekifi T., Rabeh, A., Alhussan A.A. Assessing suitable areas for PV power installation in remote agricultural regions. Energies, 2024, vol. 17 (22), 5792.
7. Ladjal B., Tibermacine I.E., Bechouat M., Sedraoui M., Napoli C., Rabehi A., Lalmi D. Hybrid models for direct normal irradiance forecasting: a case study of Ghardaia zone (Algeria). Natural Hazards, 2024, pp. 1–23.
8. Louzazni Mohamed. A non-linear auto-regressive exogenous method to forecast the photovoltaic power output. Sustainable Energy Technologies and Assessment, 2020, vol. 38, 100670.
9. Cherier Mohamed Kamal. Multi‐hour ahead forecasting of building energy through a new integrated model. Environmental Progress & Sustainable Energy, 2022, vol. 41.5, e13823.
10. Sun Yujing. Research on short-term module temperature prediction model based on BP neural network for photovoltaic power forecasting. 2015 IEEE power & energy society general meeting. IEEE, 2015.
11. Wang Lishu. The short-term forecasting of asymmetry photovoltaic power based on the feature extraction of PV power and SVM algorithm. Symmetry, 2020, vol. 12.11, 1777.
12. Ding Ming, Lei Wang, Rui Bi. An ANN-based approach for forecasting the power output of photovoltaic system. Procedia Environmental Sciences, 2011, vol. 11, pp. 1308–1315.
13. Ma W., Chen Z., Zhu Q. Ultra-short-term forecasting of photovoltaic power via RBF Neural Network. Electronics, 2020.
14. Boulmaiz T., Mawloud Guermoui, Hamouda Boutaghane. Impact of training data size on the LSTM performances for rainfall–runoff modeling. Modeling Earth Systems and Environment 2020, vol. 6, pp. 2153–2164.
15. Wang Kejun, Xiaoxia Qi, Hongda Liu. Photovoltaic power forecasting-based LSTM-Convolutional Network. Energy, 2019, vol. 189, 116225.
16. Konstantinou M., Peratikou S., Charalambides A.G. Solar photovoltaic forecasting of power output using LSTM networks. Atmosphere, 2021, vol. 12.1, 124.
17. Ahmed Razin. A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization. Renewable and Sustainable Energy Reviews, 2020, vol. 124, 109792.
18. Ferkous Khaled. A novel learning approach for short-term photovoltaic power forecasting – a review and case studies. Engineering Applications of Artificial Intelligence, 2024, vol. 133, 108502.
19. Guermoui Mawloud. A comprehensive review of hybrid models for solar radiation forecasting. Journal of Cleaner Production, 2020, vol. 258, 120357.
20. Qing Xiangyun, Yugang Niu. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 2018, vol. 148, pp. 461–468.
21. Khelifi Reski. Short‐term PV power forecasting using a hybrid TVF‐EMD‐ELM strategy. International Transactions on Electrical Energy Systems, 2023, vol. 2023.1, 6413716.
22. Guermoui Mawloud. Potential assessment of the TVF-EMD algorithm in forecasting hourly global solar radiation: review and case studies. Journal of Cleaner Production, 2023, vol. 385, 135680.
23. Zhen Hao. Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information. Energy, 2021, vol. 231, 120908.
24. Korkmaz D. SolarNet: a hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting. Applied Energy, 2021, vol. 300, 117410.
25. Jia Pengyun. Short-term photovoltaic power forecasting based on VMD and ISSA-GRU. IEEE Access, 2021, vol. 9, pp. 105939–105950.
26. Wang Hui, Jianbo Sun, Weijun Wang. Photovoltaic power forecasting based on EEMD and a variable-weight combination forecasting model. Sustainability, 2018, vol. 10.8, 2627.
27. Wang Shuaijie, Shu Liu, Xin Guan. Ultra-short-term power prediction of a photovoltaic power station based on the VMD-CEEMDAN-LSTM model. Frontiers in Energy Research, 2022, vol. 10, 945327.
28. He Yutong. Short-term photovoltaic power forecasting method based on convolutional neural network. Energy Reports, 2022, vol. 8, pp. 54–62.
29. Behera Manoja Kumar, Niranjan Nayak. A comparative study on short-term PV power forecasting using decomposition based optimized extreme learning machine algorithm. Engineering Science and Technology, an International Journal, 2020, vol. 23.1, pp. 156–167.
30. Li Pengtao. A hybrid deep learning model for short-term PV power forecasting. Applied Energy, 2020, vol. 259, 114216.
31. Kumari Pratima, Durga Toshniwal. Long short term memory – convolutional neural network based deep hybrid approach for solar irradiance forecasting. Applied Energy, 2021, vol. 295, 117061.
32. Zhang Chu, Tian Peng, Muhammad Shahzad Nazir. A novel integrated photovoltaic power forecasting model based on variational mode decomposition and CNN-BiGRU considering meteorological variables. Electric Power Systems Research, 2022, vol. 213, 108796.
33. Netsanet S. Short-term PV power forecasting using variational mode decomposition integrated with Ant colony optimization and neural network. Energy Reports, 2022, vol. 8.
34. Niu Dongxiao. Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: a case study. Applied soft computing, 2020, vol. 93, 106389.
35. Ma Yanhong. Short-term photovoltaic power forecasting method based on irradiance correction and error forecasting. Energy Reports, 2021, vol. 7, pp. 5495–5509.
36. Gupta Priya, Rhythm Singh. Combining a deep learning model with multivariate empirical mode decomposition for hourly global horizontal irradiance forecasting. Renewable Energy, 2023, vol. 206, pp. 908–927.
37. Abdel-Nasser Mohamed, Karar Mahmoud. Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural computing and applications, 2019, vol. 31, pp. 2727–2740.
38. Guermoui Mawloud, Boland J., Abdelaziz Rabehi. On the use of BRL model for daily and hourly solar radiation components assessment in a semiarid climate. The European Physical Journal Plus, 2020, vol. 135.2, pp. 1–16.
39. Guermoui Mawloud. An analysis of case studies for advancing photovoltaic power forecasting through multi-scale fusion techniques. Scientific Reports, 2024, vol. 14.1, 6653.
40. Global Solar Atlas. Available at: https://globalsolaratlas.info/map (15 January 2025).
41. Guermoui Mawloud. A novel ensemble learning approach for hourly global solar radiation forecasting. Neural Computing and Applications, 2022, pp. 1–23.
42. Mellit A., Massi Pavan A., Lughi V. Deep learning neural networks for short-term photovoltaic power forecasting. Renewable Energy, 2021, vol. 172, pp. 276–288.
43. Wang Yusen, Wenlong Liao, Yuqing Chang. Gated recurrent unit network-based short-term photovoltaic forecasting. Energies, 2018, vol. 11.8, 2163.
44. Li Jie. Prediction of short-term photovoltaic power via self-attention-based deep learning approach. Journal of Energy Resources Technology, 2022, vol. 144.10, 101301.
45. Rabehi Abdelaziz. Decomposing global solar radiation into its diffuse and direct normal radiation. International Journal of Ambient Energy, 2020, vol. 41.7, pp. 738–743.
46. Marzouglal M., Souahlia A., Bessissa L., Mahi D., Rabehi A., Alharthi Y.Z., Ghoneim S.S. Prediction of power conversion efficiency parameter of inverted organic solar cells using artificial intelligence techniques. Scientific Reports, 2024, vol. 14 (1), 25931.
47. Teta A., Korich B., Bakria D., Hadroug N., Rabehi A., Alsharef M., Ghoneim S.S. Fault detection and diagnosis of grid-connected photovoltaic systems using energy valley optimizer based lightweight CNN and wavelet transform. Scientific Reports, 2024, vol. 14 (1), 18907.
48. El-Amarty N., Marzouq M., El Fadili H., Bennani S.D., Ruano A., Rabehi A. A new evolutionary forest model via incremental tree selection for short-term global solar irradiance forecasting under six various climatic zones. Energy Conversion and Management, 2024, vol. 310, 118471.
49. Bouchakour A., Zarour L., Bessous N., Bechouat M., Borni A., Zaghba L., Ghoneim S.S. MPPT algorithm based on metaheuristic techniques (PSO & GA) dedicated to improve wind energy water pumping system performance. Scientific Reports, 2024, vol. 14 (1), 17891.
