NONE 20260525073359682 wseas/wseas content-registration-form+ja@crossref.org content-registration-form WSEAS TRANSACTIONS ON POWER SYSTEMS 1790-5060 2224-350X Khaled Ferkous Laboratory of Materials, Technology of Energy Systems and Environment (LMTESE) Univercité de Ghardaia, ALGERIA Belgacem Bekkar Laboratory of Materials, Technology of Energy Systems and Environment (LMTESE) Univercité de Ghardaia, ALGERIA Sarra Menakh Laboratory of New and Renewable Energy in Aride Zones (LENREZA), University Kasdi Merbah – Ouargla, ALGERIA Mawloud Guermoui Renewable Energy Applied Research Unit (URAER), Ghardaia, ALGERIA Predicting how much power solar panels will produce is a major hurdle for stable energy grids, largely because solar output is notoriously unpredictable, nonlinear, and constantly shifting. To tackle this, we’ve developed a hybrid deep learning framework designed for more accurate short-term forecasting. Our approach uses "CEEMDAN" to break down complex solar data into manageable components, paired with Iterative Filtering (IF) to pull out the most meaningful hidden patterns. These refined insights are then processed through a Bidirectional Long Short-Term Memory ("BiLSTM" ) network. By combining these tools, our model captures the deep, time-sensitive relationships in solar generation that traditional methods often miss. Each component is then modeled using "BiLSTM" networks to capture bidirectional temporal dependencies, and the final forecast is obtained through signal reconstruction. The proposed model is evaluated using real-world PV datasets collected from Tindouf (Algeria), and its performance is compared with benchmark deep learning and decomposition-based approaches. Testing proves that this framework markedly boosts both the accuracy and reliability of solar power predictions. With an R^2 of 99.06 %, an "RMSE" of 158.20 "kW" , and an "nRMSE" of 6.15%, the model consistently leads the way over standard LSTM models and other hybrid setups. These outcomes validate the idea that combining "CEEMDAN" decomposition, precise time-frequency feature extraction, and bidirectional deep learning creates a powerful, dependable solution for short-term forecasting. By blending these specific techniques, the system manages to capture the nuance of solar data more effectively than previous methods. 12 31 2025 12 31 2025 519 42 https://creativecommons.org/licenses/by/4.0/deed.en_US 10.37394/232016.2025.20.42 https://wseas.com/journals/ps/2025/a845116-025(2025).pdf Y. Liu, J. Wang, L. Song, Y. Liu and L. Shen, "Enhanced Short-Term PV Power Forecasting via a Hybrid Modified CEEMDAN-Jellyfish Search Optimized BiLSTM Model," Energies, vol. 18, no. 13, p. 3581, 2025, doi: 10.3390/en18133581. Y. Li, S. Zhai, G. Yi, S. Pang and X. Luo, "Short-Term Photovoltaic Power Forecasting Based on ICEEMDAN-TCN-BiLSTM-MHA," Symmetry, vol. 17, p. 1599, 2025, doi: 10.3390/sym17101599. J. Zhang, Y. Hao, R. Fan and Z. Wang, "An Ultra-Short-Term PV Power Forecasting Method for Changeable Weather Based on Clustering and Signal Decomposition," Energies, vol. 16, no. 7, p. 3092, 2023, doi: 10.3390/en16073092. R. Zhang, Z. Xu, S. Liu, K. Fu and J. Zhang, "Prediction of Ultra-Short-Term Photovoltaic Power Using BiLSTM–Informer Based on Secondary Decomposition," Energies, vol. 18, p. 1485, 2025, doi: 10.3390/en18061485. D. Zhou, Y. Liu, X. Wang, F. Wang and Y. Jia, "Combined ultra-short-term photovoltaic power prediction based on CEEMDAN decomposition and RIME optimized AM-TCN-BiLSTM," Energy, vol. 318, p. 134847, 2025, doi: 10.1016/j.energy.2025.134847. J. Liang, L. Yin, Y. Xin, S. Li, Y. Zhao and T. Song, "Short-term photovoltaic power prediction based on CEEMDAN-PE and BiLSTM neural network," Electric Power Systems Research, vol. 246, p. 111706, 2025, doi: 10.1016/j.epsr.2025.111706. M. Liu, X. Wang and Z. Zhong, "Ultra-ShortTerm Photovoltaic Power Prediction Based on BiLSTM with Wavelet Decomposition and Dual Attention Mechanism," Electronics, vol. 14, p. 306, 2025, doi: 10.3390/electronics14020306. N. Zhang, Q. Ren, G. Liu, L. Guo and J. Li, "Short-term PV Output Power Forecasting Based on CEEMDAN-AE-GRU," Journal of Electrical Engineering & Technology, vol. 17, pp. 1183-1194, 2022, doi: 10.1007/s42835- 021-00975-3. M. Ajith and M. Martínez-Ramón, "Deep learning algorithms for very short term solar irradiance forecasting: A survey," Renewable and Sustainable Energy Reviews, vol. 182, p. 113362, 2023, doi:10.1016/j.rser.2023.113362. A. Brihmat, H. Mahcene, D. Bechki, H. Bouguettaia, A. Khechekhouche and S. Boughali, "Energy Performance Improvement of a Solar Still System Using Date and Olive Kernels: Experimental Study," CLEAN – Soil, Air, Water, vol. 51, p. 2200384, 2023, doi: 10.1002/clen.202200384. N. Zhang, S. Wang, G. C. Liu and J. W. Zhang, "All-factor short-term photovoltaic output power forecast," IET Renewable Power Generation, vol. 16, pp. 148-158, 2022, doi: 10.1049/rpg2.12274. A. Yadav and S. Chandel, "Solar radiation prediction using Artificial Neural Network techniques: A review," Renewable and Sustainable Energy Reviews, vol. 33, pp. 772- 781, 2014, doi: 10.1016/j.rser.2013.08.055. S. S. Chandel, A. Gupta, R. Chandel and S. Tajjour, "Review of deep learning techniques for power generation prediction of industrial solar photovoltaic plants," Solar Compass, vol. 8, p. 100061, 2023, doi: 10.1016/j.solcom.2023.100061. K. Ferkous, F. Chellali, A. Kouzou and B. Bekkar, "Wavelet-Gaussian Process Regression Model for Regression Daily Solar Radiation in Ghardaia, Algeria," Instrumentation Mesure Métrologie, vol. 20, pp. 113-119, 2021, doi: 10.18280/i2m.200208. C. Guo, X. Kang, J. Xiong and J. Wu, "A New Time Series Forecasting Model Based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Temporal Convolutional Network," Neural Processing Letters, vol. 55, pp. 4397-4417, 2023, doi: 10.1007/s11063-022-11046-7. R. Prasad, M. Ali, Y. Xiang and H. Khan, "A double decomposition-based modelling approach to forecast weekly solar radiation," Renewable Energy, vol. 152, pp. 9-22, 2020, doi: 10.1016/j.renene.2020.01.005. H. Wang, J. Sun and W. Wang, "Photovoltaic Power Forecasting Based on EEMD and a Variable-Weight Combination Forecasting Model," Sustainability, vol. 10, p. 2627, 2018, doi: 10.3390/su10082627. D. Niu, K. Wang, L. Sun, J. Wu and X. Xu, "Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study," Applied Soft Computing, vol. 93, p. 106389, 2020, doi: 10.1016/j.asoc.2020.106389. C. Zhang, T. Peng and M. S. Nazir, "A novel integrated photovoltaic power forecasting model based on variational mode decomposition and CNN-BiGRU considering meteorological variables," Electric Power Systems Research, vol. 213, p. 108796, 2022, doi: 10.1016/j.epsr.2022.108796. T. Li, Z. Qian and T. He, "Short-Term Load Forecasting with Improved CEEMDAN and GWO-Based Multiple Kernel ELM," Complexity, vol. 2020, p. 1209547, 2020, doi: 10.1155/2020/1209547. H. Feng and C. Yu, "A novel hybrid model for short-term prediction of PV power based on KS-CEEMDAN-SE-LSTM," Renewable Energy Focus, vol. 47, p. 100497, 2023, doi: 10.1016/j.ref.2023.100497. U. K. Das, K. S. Tey, M. Seyedmahmoudian, S. Mekhilef, M. Y. I. Idris, W. Van Deventer, B. Horan and A. Stojcevski, "Forecasting of photovoltaic power generation and model optimization: A review," Renewable and Sustainable Energy Reviews, vol. 81, pp. 912- 928, 2018, doi: 10.1016/j.rser.2017.08.017. S. M. Al-Selwi, M. F. Hassan, S. J. Abdulkadir, A. Muneer, E. H. Sumiea, A. Alqushaibi and M. G. Ragab, "RNN-LSTM: From applications to modeling techniques and beyond—Systematic review," Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 5, p. 102068, 2024, doi: 10.1016/j.jksuci.2024.102068. H. Abbasimehr and R. Paki, "Improving time series forecasting using LSTM and attention models," Journal of Ambient Intelligence and Humanized Computing, vol. 13, no. 1, pp. 673- 691, 2022, doi: 10.1007/s12652-020-02761-x. K. Ferkous, T. Boulmaiz, F. A. Ziari and B. Bekkar, "A hybrid approach based on complete ensemble empirical mode decomposition with adaptive noise for multi-step-ahead solar radiation forecasting," Clean Energy, vol. 6, pp. 705-715, 2022, doi: 10.1093/ce/zkac045. R. Bai, J. Li, J. Liu, Y. Shi, S. He and W. Wei, "Day-ahead photovoltaic power generation forecasting with the HWGC-WPD-LSTM hybrid model assisted by wavelet packet decomposition and improved similar day method," Engineering Science and Technology, an International Journal, vol. 61, p. 101889, 2025, doi: 10.1016/j.jestch.2024.101889. Y. Qu, J. Xu, Y. Sun and D. Liu, "A temporal distributed hybrid deep learning model for dayahead distributed PV power forecasting," Applied Energy, vol. 304, p. 117704, 2021, doi: 10.1016/j.apenergy.2021.117704. N. L. M. Jailani, J. K. Dhanasegaran, G. Alkawsi, A. A. Alkahtani, C. C. Phing, Y. Baashar, L. F. Capretz, A. Q. Al-Shetwi and S. K. Tiong, "Investigating the Power of LSTMBased Models in Solar Energy Forecasting," Processes, vol. 11, p. 1382, 2023, doi: 10.3390/pr11051382. K. Ferkous, M. Guermoui, S. Menakh, A. Bellaour and T. Boulmaiz, "A novel learning approach for short-term photovoltaic power forecasting - A review and case studies," Engineering Applications of Artificial Intelligence, vol. 133, p. 108502, 2024, doi: 10.1016/j.engappai.2024.108502. L. Cao, H. Yang, C. Zhou, S. Wang, Y. Shen and B. Yuan, "Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long ShortTerm Memory," Energies, vol. 17, p. 6365, 2024, doi: 10.3390/en17246365.