Forecasting Renewable Energy Employing A Regularized Deep Learning Approach

It can be concluded that forecasting renewable energy is a critical need of the present times. The proposed DWT-BR-DNN framework can support different solar energy forecasting applications. In short-term forecasting, the model can predict solar power generation over the next several minutes or hours, supporting real-time power dispatch, grid balancing, and battery management. In day-ahead forecasting, the model can estimate expected solar energy production for the following day, enabling electricity scheduling and energy market planning. In longer-term applications, the framework may support energy assessment and operational planning when suitable historical data and relevant seasonal information are available. The prediction model can also be integrated with smart-grid management systems to estimate the expected contribution of photovoltaic installations to the electricity supply. The proposed approach combines DWT-BRDNN and attains an MAE value of just 3.0 clearly outperforming baseline approaches in the domain.

[1]   K Abbass, MZ Qasim, H Song, M Murshed, “A review of the global climate change impacts, adaptation, and sustainable mitigation measures”, Environmental Science and Pollution Research, Springer 2023, vol.29, pp. 42539–42559. [2]   J. Luo, W. Zhuo, S. Liu and B. Xu, "The Optimization of Carbon Emission Prediction in Low Carbon Energy Economy Under Big Data," in IEEE Access, 2024,vol. 12, pp. 14690-14702. [3]   Y. Chen, H. Zhang and F. -Y. Wang, "Society-Centered and DAO-Powered Sustainability in Transportation 5.0: An Intelligent Vehicles Perspective," in IEEE Transactions on Intelligent Vehicles, 2023, vol. 8, no. 4, pp. 2635-2638. [4]   B. Kroposki and A. Hoke, "A Path to 100 Percent Renewable Energy: Grid-Forming Inverters will Give Us the Grid We Need Now," in IEEE Spectrum, vol. 61, no. 5, pp. 50-57, May 2024. [5]   W. Ahmed et al., "Machine Learning Based Energy Management Model for Smart Grid and Renewable Energy Districts," in IEEE Access, vol. 8, pp. 185059-185078, 2020. [6]   G. Li, S. Xie, B. Wang, J. Xin, Y. Li and S. Du, "Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach," in IEEE Access, vol. 8, pp. 175871-175880, 2020,. [7]   L. F. J. Alvarez, S. R. González, A. D. López, D. A. H. Delgado, R. Espinosa and S. Gutiérrez, "Renewable Energy Prediction through Machine Learning Algorithms," 2020 IEEE ANDESCON, Quito, Ecuador, 2020, pp. 1-6/ [8]   M. A. Muñoz, J. M. Morales and S. Pineda, "Feature-Driven Improvement of Renewable Energy Forecasting and Trading," in IEEE Transactions on Power Systems, vol. 35, no. 5, pp. 3753-3763, Sept. 2020. [9]   N. Shabbir, R. AhmadiAhangar, L. Kütt, M. N. Iqbal and A. Rosin, "Forecasting Short Term Wind Energy Generation using Machine Learning," 2019 IEEE 60th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON), Riga, Latvia, 2019, pp. 1-4. [10]          S. Shamshirband, T. Rabczuk and K. -W. Chau, "A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources," in IEEE Access, vol. 7, pp. 164650-164666, 2019.