volume | PIER Journals

Abstract

To address the randomness and nonlinearity of photovoltaic (PV) power caused by meteorological factors, this paper proposes an ICEEMDAN-WOA-CNN-BiLSTM prediction model integrated with fuzzy entropy clustering and a self-attention mechanism. First, the original PV power sequence is decomposed into multiple multi-scale intrinsic mode function (IMF) components and residuals via the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN). Subsequently, components with similar complexity are merged using fuzzy entropy clustering to simplify the calculations. Then, the Whale Optimization Algorithm (WOA) is adopted to optimize the hyperparameters of the CNN-BiLSTM model, and the self-attention mechanism is integrated into the model to enhance the weights of key features. Comparative experiments demonstrate that the proposed model significantly outperforms single and traditional hybrid models in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). This can effectively improve the accuracy of short-term PV power prediction and provide support for power station dispatching and power grid stability.

1. Shi, Jingli and Yue Zhao, "Challenges and pathways for tripling renewable energy capacity globally by 2030," Chinese Journal of Urban and Environmental Studies, Vol. 13, No. 1, 2550004, 2025.
doi:10.1142/s2345748125500046 Google Scholar

2. Liu, Yingying and Zhongping Wang, "Robust and efficient multihorizon photovoltaic power forecasting with a dilated multi-scale transformer," Solar Energy, Vol. 302, 114077, 2025.
doi:10.1016/j.solener.2025.114077 Google Scholar

3. Li, Jun and Qibo Liu, "Forecasting of short-term photovoltaic power generation using combined interval type-2 Takagi-Sugeno-Kang fuzzy systems," International Journal of Electrical Power & Energy Systems, Vol. 140, 108002, 2022.
doi:10.1016/j.ijepes.2022.108002 Google Scholar

4. Erdener, Burcin Cakir, Cong Feng, Kate Doubleday, Anthony Florita, and Bri-Mathias Hodge, "A review of behind-the-meter solar forecasting," Renewable and Sustainable Energy Reviews, Vol. 160, 112224, 2022.
doi:10.1016/j.rser.2022.112224 Google Scholar

5. Wang, Kejun, Xiaoxia Qi, and Hongda Liu, "A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network," Applied Energy, Vol. 251, 113315, 2019.
doi:10.1016/j.apenergy.2019.113315 Google Scholar

6. Gaboitaolelwe, Jwaone, Adamu Murtala Zungeru, Abid Yahya, Caspar K. Lebekwe, Dasari Naga Vinod, and Ayodeji Olalekan Salau, "Machine learning based solar photovoltaic power forecasting: A review and comparison," IEEE Access, Vol. 11, 40820-40845, 2023.
doi:10.1109/access.2023.3270041 Google Scholar

7. Gigoni, Lorenzo, Alessandro Betti, Emanuele Crisostomi, Alessandro Franco, Mauro Tucci, Fabrizio Bizzarri, and Debora Mucci, "Day-ahead hourly forecasting of power generation from photovoltaic plants," IEEE Transactions on Sustainable Energy, Vol. 9, No. 2, 831-842, 2018.
doi:10.1109/tste.2017.2762435 Google Scholar

8. Colbu, Ștefania-Cristiana, Daniel-Marian Bancila, and Dumitru Popescu, "Long-term power generation prediction in photovoltaics using machine learning-based models," Romanian Journal of Information Science and Technology (ROMJIST), Vol. 28, No. 1, 39-50, 2025.
doi:10.59277/ROMJIST.2025.1.04 Google Scholar

9. Rao, Zhi, Zaimin Yang, Jiaming Li, Lifeng Li, and Siyang Wan, "Prediction of photovoltaic power generation based on parallel bidirectional long short-term memory networks," Energy Reports, Vol. 12, 3620-3629, 2024.
doi:10.1016/j.egyr.2024.09.043 Google Scholar

10. Kumar, Anil, Yashwant Kashyap, and Rehan Nasar, "Enhancing high-frequency PV power forecast using optimal hyperparameter setting in LSTM," International Conference on Sustainable Power and Energy Research, 165-174, Warangal, India, 2024.
doi:10.1007/978-981-96-0824-9_15

11. Iheanetu, Kelachukwu J., "Solar photovoltaic power forecasting: A review," Sustainability, Vol. 14, No. 24, 17005, 2022.
doi:10.3390/su142417005 Google Scholar

12. Ait Abdelmoula, Ibtihal, Said Elhamaoui, Omaima Elalani, Abdellatif Ghennioui, and Mohamed El Aroussi, "A photovoltaic power prediction approach enhanced by feature engineering and stacked machine learning model," Energy Reports, Vol. 8, 1288-1300, 2022.
doi:10.1016/j.egyr.2022.07.082 Google Scholar

13. Xiao, Zenan, Xiaoqiao Huang, Jun Liu, Chengli Li, and Yonghang Tai, "A novel method based on time series ensemble model for hourly photovoltaic power prediction," Energy, Vol. 276, 127542, 2023.
doi:10.1016/j.energy.2023.127542 Google Scholar

14. Su, Zibo, Chaojun Shi, Ke Zhang, Xiongbin Xie, Xiaoyun Zhang, and Junchi Xiao, "TransFCloudNet: A dual-branch feature fusion ground-based cloud image fine-grained segmentation method for photovoltaic power prediction," Energy Conversion and Management, Vol. 348, 120647, 2026.
doi:10.1016/j.enconman.2025.120647 Google Scholar

15. Zhang, Ruoqi, Zishuo Xu, Shuangquan Liu, Kaixiang Fu, and Jie Zhang, "Prediction of ultra-short-term photovoltaic power using BiLSTM-informer based on secondary decomposition," Energies, Vol. 18, No. 6, 1485, 2025.
doi:10.3390/en18061485 Google Scholar

16. Fang, Xin, Shaohua Han, Juan Li, Jiaming Wang, Mingming Shi, Yunlong Jiang, Chenyu Zhang, and Jian Sun, "A FCM-XGBoost-GRU model for short-term photovoltaic power forecasting based on weather classification," 2023 5th Asia Energy and Electrical Engineering Symposium (AEEES), 1444-1449, Chengdu, China, Mar. 2023.
doi:10.1109/AEEES56888.2023.10114292

17. Yu, Zhongan, Faneng Wu, Long Chen, Siqi Zhu, and Junjie Zhang, "Photovoltaic power prediction model based on K-shape-NGO-CNN-BiLSTM with secondary decomposition," Progress In Electromagnetics Research C, Vol. 160, 183-195, 2025.
doi:10.2528/PIERC25081801 Google Scholar

18. Colominas, Marcelo A., Gastón Schlotthauer, and María E. Torres, "Improved complete ensemble EMD: A suitable tool for biomedical signal processing," Biomedical Signal Processing and Control, Vol. 14, 19-29, 2014.
doi:10.1016/j.bspc.2014.06.009 Google Scholar

19. Zheng, Jinde, Haiyang Pan, and Junsheng Cheng, "Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines," Mechanical Systems and Signal Processing, Vol. 85, 746-759, 2017.
doi:10.1016/j.ymssp.2016.09.010 Google Scholar

20. Mirjalili, Seyedali and Andrew Lewis, "The whale optimization algorithm," Advances in Engineering Software, Vol. 95, 51-67, 2016.
doi:10.1016/j.advengsoft.2016.01.008 Google Scholar

21. Han, Haotong, Jishen Peng, Jun Ma, Shang Lin Liu, and Hao Liu, "Research on load forecasting based on CEEMDAN SE VMD and SelfAttention TCN fusion model," Scientific Reports, Vol. 15, No. 1, 14530, 2025.
doi:10.1038/s41598-025-98224-4 Google Scholar

22. Agga, Ali, Ahmed Abbou, Moussa Labbadi, Yassine El Houm, and Imane Hammou Ou Ali, "CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production," Electric Power Systems Research, Vol. 208, 107908, 2022.
doi:10.1016/j.epsr.2022.107908 Google Scholar

23. Liang, Jianwei, Liying Yin, Yanli Xin, Sichao Li, Yuqian Zhao, and Tian Song, "Short-term photovoltaic power prediction based on CEEMDAN-PE and BiLSTM neural network," Electric Power Systems Research, Vol. 246, 111706, 2025.
doi:10.1016/j.epsr.2025.111706 Google Scholar

Dr. Zhongan Yu

Mr. Faneng Wu

Dr. Zhiwei Huang

Dr. Zihao Deng

Dr. Feng Zhang