Leveraging advanced AI algorithms with transformer-infused recurrent neural networks to optimize solar irradiance forecasting

被引：0
作者：
Naveed, M.S. [1 ]
Hanif, M.F. [1 ,2 ]
Metwaly, M. [3 ]
Iqbal, I. [4 ]
Lodhi, E. [5 ]
Liu, X. [1 ]
Mi, J. [1 ]
机构：
[1] Department of Energy and Resource Engineering, College of Engineering, Peking University, Beijing
[2] Department of Mechanical Engineering, Faculty of Engineering and Technology, Bahauddin Zakariya University, Multan
[3] Archaeology Department, College of Tourism and Archaeology, King Saud University, Riyadh
[4] Department of PLR, Institute of Active Polymers, Helmholtz-Zentrum Hereon, Teltow
[5] Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang, Haining
来源：
Frontiers in Energy Research | 2024年 / 12卷
关键词：
bidirectional LSTM model; deep Learning; GRU model; solar forecasting; solar irradiance; transformer model;
D O I：
10.3389/fenrg.2024.1485690
中图分类号：
学科分类号：
摘要：
Solar energy (SE) is vital for renewable energy generation, but its natural fluctuations present difficulties in maintaining grid stability and planning. Accurate forecasting of solar irradiance (SI) is essential to address these challenges. The current research presents an innovative forecasting approach named as Transformer-Infused Recurrent Neural Network (TIR) model. This model integrates a Bi-Directional Long Short-Term Memory (BiLSTM) network for encoding and a Gated Recurrent Unit (GRU) network for decoding, incorporating attention mechanisms and positional encoding. This model is proposed to enhance SI forecasting accuracy by effectively utilizing meteorological weather data, handling overfitting, and managing data outliers and data complexity. To evaluate the model’s performance, a comprehensive comparative analysis is conducted, involving five algorithms: Artificial Neural Network (ANN), BiLSTM, GRU, hybrid BiLSTM-GRU, and Transformer models. The findings indicate that employing the TIR model leads to superior accuracy in the analyzed area, achieving R2 value of 0.9983, RMSE of 0.0140, and MAE of 0.0092. This performance surpasses those of the alternative models studied. The integration of BiLSTM and GRU algorithms with the attention mechanism and positional encoding has been optimized to enhance the forecasting of SI. This approach mitigates computational dependencies and minimizes the error terms within the model. Copyright © 2024 Naveed, Hanif, Metwaly, Iqbal, Lodhi, Liu and Mi.
引用
收藏
相关论文
共 78 条
  • [71] Yang K., Koike T., Ye B., Improving estimation of hourly, daily, and monthly solar radiation by importing global data sets, Agric Meteorol, 137, 1–2, pp. 43-55, (2006)
  • [72] Yang Y., Wu Q.M.J., Feng X., Akilan T., Recomputation of dense layers for the performance improvement of DCNN, IEEE Trans. Pattern Anal. Mach. Intell, 42, 11, (2020)
  • [73] Zang H., Liu L., Sun L., Cheng L., Wei Z., Sun G., Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations, Renew. Energy, 160, pp. 26-41, (2020)
  • [74] Zhang J., Zhong A., Huang G., Yang M., Li D., Teng M., Et al., Enhanced efficiency with CDCA co-adsorption for dye-sensitized solar cells based on metallosalophen complexes, Sol. Energy, 209, pp. 316-324, (2020)
  • [75] Zhong C., Lai C.S., Ng W.W.Y., Tao Y., Wang T., Lai L.L., Multi-view deep forecasting for hourly solar irradiance with error correction, Sol. Energy, 228, pp. 308-316, (2021)
  • [76] Zhou C., Chen X., Predicting China’s energy consumption: combining machine learning with three-layer decomposition approach, Energy Rep, 7, pp. 5086-5099, (2021)
  • [77] Zhou H., Deng Z., Xia Y., Fu M., A new sampling method in particle filter based on Pearson correlation coefficient, Neurocomputing, 216, pp. 208-215, (2016)
  • [78] Zhu T., Li Y., Li Z., Guo Y., Ni C., Inter-hour forecast of solar radiation based on long short-term memory with attention mechanism and genetic algorithm, Energies (Basel), 15, 3, (2022)
12345678