volume | PIER Journals

Abstract

With the development of the photovoltaic industry, accurate power prediction is critical to grid stability. To address photovoltaic power's high sensitivity to meteorological conditions, nonlinearity, and non-stationarity, this paper develops a prediction model that integrates multi-scale features and intelligent optimization. First, correlation coefficients are used to screen key weather factors, and K-shape clustering is applied to classify operational scenarios into sunny, cloudy, and rainy types. For the power data of each scenario, multi-scale features are extracted via Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), sample entropy secondary clustering, and Variational Mode Decomposition (VMD)-based deep decomposition. After fusing these features with weather factors, the integrated data is input into a Convolutional Neural Network-Bidirectional Long Short-Term Memory Network (CNN-BiLSTM), with hyperparameters optimized using the Northern Goshawk Optimization (NGO) algorithm. Verification with actual datasets indicates that this model outperforms traditional counterparts. Specifically, compared with the traditional BiLSTM model, its Mean Absolute Error (MAE) is reduced by 70.8%, 20.7%, and 47.0% under sunny, cloudy, and rainy scenarios, respectively - providing effective support for efficient dispatching and stable operation of photovoltaic power grids.

1. Yi, Tao, Ling Tong, Mohan Qiu, and Jinpeng Liu, "Analysis of driving factors of photovoltaic power generation efficiency: A case study in China," Energies, Vol. 12, No. 3, 355, 2019.
doi:10.3390/en12030355

2. Xu, Xinkuo, Chengmei Guan, and Jiayu Jin, "Valuing the carbon assets of distributed photovoltaic generation in China," Energy Policy, Vol. 121, 374-382, 2018.
doi:10.1016/j.enpol.2018.06.046

3. Başaran, Kıvanç, Fatma Bozyiğit, Pierluigi Siano, Pelin Yıldırım Taşer, and Deniz Kılınç, "Systematic literature review of photovoltaic output power forecasting," IET Renewable Power Generation, Vol. 14, No. 19, 3961-3973, 2020.
doi:10.1049/iet-rpg.2020.0351

4. Sobri, Sobrina, Sam Koohi-Kamali, and Nasrudin Abd. Rahim, "Solar photovoltaic generation forecasting methods: A review," Energy Conversion and Management, Vol. 156, 459-497, 2018.
doi:10.1016/j.enconman.2017.11.019

5. 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

6. Tina, Giuseppe Marco, Cristina Ventura, Sergio Ferlito, and Saverio De Vito, "A state-of-art-review on machine-learning based methods for PV," Applied Sciences, Vol. 11, No. 16, 7550, 2021.
doi:10.3390/app11167550

7. Yu, Junfeng, Xiaodong Li, Lei Yang, Linze Li, Zhichao Huang, Keyan Shen, Xu Yang, Xu Yang, Zhikang Xu, Dongying Zhang, and Shuai Du, "Deep learning models for PV power forecasting: Review," Energies, Vol. 17, No. 16, 3973, 2024.
doi:10.3390/en17163973

8. Das, Utpal Kumar, Kok Soon Tey, Mehdi Seyedmahmoudian, Saad Mekhilef, Moh Yamani Idna Idris, Willem Van Deventer, Bend Horan, and Alex Stojcevski, "Forecasting of photovoltaic power generation and model optimization: A review," Renewable and Sustainable Energy Reviews, Vol. 81, 912-928, 2018.
doi:10.1016/j.rser.2017.08.017

9. Massidda, Luca and Marino Marrocu, "Use of multilinear adaptive regression splines and numerical weather prediction to forecast the power output of a PV plant in Borkum, Germany," Solar Energy, Vol. 146, 141-149, 2017.
doi:10.1016/j.solener.2017.02.007

10. Li, Yanting, Yong He, Yan Su, and Lianjie Shu, "Forecasting the daily power output of a grid-connected photovoltaic system based on multivariate adaptive regression splines," Applied Energy, Vol. 180, 392-401, 2016.
doi:10.1016/j.apenergy.2016.07.052

11. Buonanno, Amedeo, Giampaolo Caputo, Irena Balog, Salvatore Fabozzi, Giovanna Adinolfi, Francesco Pascarella, Gianni Leanza, Giorgio Graditi, and Maria Valenti, "Machine learning and weather model combination for PV production forecasting," Energies, Vol. 17, No. 9, 2203, 2024.
doi:10.3390/en17092203

12. Wu, Ze, Feifan Pan, Dandan Li, Hao He, Tiancheng Zhang, and Shuyun Yang, "Prediction of photovoltaic power by the informer model based on convolutional neural network," Sustainability, Vol. 14, No. 20, 13022, 2022.
doi:10.3390/su142013022

13. Liang, Jianwei, Liying Yin, Sichao Li, Xiubin Zhu, Zhangshen Liu, and Yanli Xin, "Photovoltaic power prediction based on K-means++-BiLSTM-transformer," Progress In Electromagnetics Research C, Vol. 154, 191-201, 2025.
doi:10.2528/pierc25021303

14. Zeng, Ailing, Muxi Chen, Lei Zhang, and Qiang Xu, "Are transformers effective for time series forecasting?," Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, No. 9, 11121-11128, Washington, USA, Jun. 2023.
doi:10.1609/aaai.v37i9.26317

15. Yu, Chengqing, Fei Wang, Zezhi Shao, Tao Sun, Lin Wu, and Yongjun Xu, "Dsformer: A double sampling transformer for multivariate time series long-term prediction," Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 3062-3072, Birmingham, United Kingdom, Oct. 2023.
doi:10.1145/3583780.3614851

16. Yu, Chengming, Ji Qiao, Chao Chen, Chengqing Yu, and Xiwei Mi, "TFEformer: A new temporal frequency ensemble transformer for day-ahead photovoltaic power prediction," Journal of Cleaner Production, Vol. 448, 141690, 2024.
doi:10.1016/j.jclepro.2024.141690

17. Yu, Chengqing, Fei Wang, Zezhi Shao, Tangwen Qian, Zhao Zhang, Wei Wei, Zhulin An, Qi Wang, and Yongjun Xu, "GinAR+: A robust end-to-end framework for multivariate time series forecasting with missing values," IEEE Transactions on Knowledge and Data Engineering, Vol. 37, No. 8, 4635-4648, 2025.
doi:10.1109/tkde.2025.3569649

18. Wu, Yun, Xingyu Pan, and Jieming Yang, "VMD-Informer-DCC for photovoltaic power prediction," IEICE Transactions on Communications, Vol. E107-B, No. 7, 487-494, 2024.
doi:10.23919/transcom.2023ebp3170

19. Xu, Weihui, Zhaoke Wang, Weishu Wang, Jian Zhao, Miaojia Wang, and Qinbao Wang, "Short-term photovoltaic output prediction based on decomposition and reconstruction and XGBoost under two base learners," Energies, Vol. 17, No. 4, 906, 2024.
doi:10.3390/en17040906

20. Li, Meng, Wei Wang, Yan He, and Qinghai Wang, "Deep learning model for short-term photovoltaic power forecasting based on variational mode decomposition and similar day clustering," Computers and Electrical Engineering, Vol. 115, 109116, 2024.
doi:10.1016/j.compeleceng.2024.109116

21. Peng, Daogang, Yu Liu, Danhao Wang, Ling Luo, Huirong Zhao, and Bogang Qu, "Short-term PV-wind forecasting of large-scale regional site clusters based on FCM clustering and hybrid Inception-ResNet embedded with Informer," Energy Conversion and Management, Vol. 320, 118992, 2024.
doi:10.1016/j.enconman.2024.118992

22. Wang, Yonggang, Yilin Yao, Qiuying Zou, Kaixing Zhao, and Yue Hao, "Forecasting a short-term photovoltaic power model based on improved snake optimization, convolutional neural network, and bidirectional long short-term memory network," Sensors, Vol. 24, No. 12, 3897, 2024.
doi:10.3390/s24123897

23. Jiang, Jianjian, Shizhao Hu, Liang Xu, and Tianlin Wang, "Short-term PV power prediction based on VMD-CNN-IPSO-LSSVM hybrid model," International Journal of Low-Carbon Technologies, Vol. 19, 1160-1167, 2024.
doi:10.1093/ijlct/ctae060

24. Paparrizos, John and Luis Gravano, "K-shape: Efficient and accurate clustering of time series," Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, 1855-1870, Melbourne Victoria, Australia, May 2015.
doi:10.1145/2723372.2737793

25. Torres, María E., Marcelo A. Colominas, Gastón Schlotthauer, and Patrick Flandrin, "A complete ensemble empirical mode decomposition with adaptive noise," 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4144-4147, Prague, Czech Republic, May 2011.
doi:10.1109/ICASSP.2011.5947265

26. Dragomiretskiy, Konstantin and Dominique Zosso, "Variational mode decomposition," IEEE Transactions on Signal Processing, Vol. 62, No. 3, 531-544, 2014.
doi:10.1109/tsp.2013.2288675

27. Dehghani, Mohammad, Štěpán Hubálovský, and Pavel Trojovský, "Northern goshawk optimization: A new swarm-based algorithm for solving optimization problems," IEEE Access, Vol. 9, 162059-162080, 2021.
doi:10.1109/access.2021.3133286

28. Zhang, Chu, Tian Peng, and 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, Vol. 213, 108796, 2022.
doi:10.1016/j.epsr.2022.108796

29. Yang, Zaimin, Lifeng Li, Zhi Rao, Wenchuan Meng, and Siyang Wan, "A short-term PV resource assessment method with parallel DenseNet201 and BiLSTM under multiple data features," Energy Reports, Vol. 11, 2841-2852, 2024.
doi:10.1016/j.egyr.2024.02.029

Dr. Zhongan Yu

Mr. Faneng Wu

Dr. Long Chen

Dr. Siqi Zhu

Dr. Junjie Zhang