IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v347y2026ics0360544226004172.html

Explainable and physics-constrained PV power prediction via a hybrid framework Integrating secondary decomposition and improved Transformer-LSTM

Author

Listed:
  • Zou, Jiahao
  • Wang, Zhaocai
  • Zhu, Zhaoyang
  • Tan, Zuowen

Abstract

Photovoltaic power generation (PVPG) is susceptible to meteorological conditions, exhibiting significant randomness and volatility. Therefore, accurate and reliable PVPG prediction is crucial for enhancing grid stability. However, existing data-driven prediction methods often overlook the system's inherent physical mechanism, which can lead to prediction results that violate actual operating laws. This study presents a physics-constrained hybrid model, integrating Transformer and Long Short-Term Memory (LSTM) networks with a secondary decomposition strategy, for the multi-step short-term forecasting of PVPG. Initially, a Seasonal and Trend Decomposition using Loess (STL) method is utilized to decompose the original dataset. Subsequently, variational mode decomposition (VMD), optimized by an improved Dream Optimization Algorithm (DOA), is utilized to decompose the residual term. Subsequently, the decomposed components and the screened features are fed into a hybrid Transformer-LSTM model, with its hyperparameter optimized by an improved Dream Optimization Algorithm, to complete the final power prediction. To ensure the predictions adhere to the physical principles of photovoltaic power generation, the model utilizes a designed physics-constrained loss function specifically. On the Australian dataset, the proposed model is evaluated and is observed to achieve better performance than other methods in both prediction accuracy and robustness. Specifically, on Site 1, the R-squared and RMSE for the overall prediction performance are 0.9423 and 0.2326, respectively, demonstrating superior prediction performance. Moreover, it also exhibits superior prediction capability across different datasets, seasons, and weather conditions. Finally, explainability analysis was conducted using SHAP method. This multi-step short-term PVPG prediction method has the potential to enhance grid stability and the stable regulation of energy.

Suggested Citation

  • Zou, Jiahao & Wang, Zhaocai & Zhu, Zhaoyang & Tan, Zuowen, 2026. "Explainable and physics-constrained PV power prediction via a hybrid framework Integrating secondary decomposition and improved Transformer-LSTM," Energy, Elsevier, vol. 347(C).
    • Handle: RePEc:eee:energy:v:347:y:2026:i:c:s0360544226004172
    DOI: 10.1016/j.energy.2026.140314
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544226004172
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2026.140314?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Liu, Xiangjie & Liu, Yuanyan & Kong, Xiaobing & Ma, Lele & Besheer, Ahmad H. & Lee, Kwang Y., 2023. "Deep neural network for forecasting of photovoltaic power based on wavelet packet decomposition with similar day analysis," Energy, Elsevier, vol. 271(C).
    2. Habib, Md. Ahasan & Hossain, M.J., 2024. "Advanced feature engineering in microgrid PV forecasting: A fast computing and data-driven hybrid modeling framework," Renewable Energy, Elsevier, vol. 235(C).
    3. Luo, Xing & Zhang, Dongxiao & Zhu, Xu, 2022. "Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants," Renewable Energy, Elsevier, vol. 185(C), pages 1062-1077.
    4. Li, Jiaqian & Rao, Congjun & Gao, Mingyun & Xiao, Xinping & Goh, Mark, 2025. "Efficient calculation of distributed photovoltaic power generation power prediction via deep learning," Renewable Energy, Elsevier, vol. 246(C).
    5. Sun, Fengpeng & Li, Longhao & Bian, Dunxin & Bian, Wenlin & Wang, Qinghong & Wang, Shuang, 2025. "Photovoltaic power prediction based on multi-scale photovoltaic power fluctuation characteristics and multi-channel LSTM prediction models," Renewable Energy, Elsevier, vol. 246(C).
    6. Chen, Jie & Peng, Tian & Qian, Shijie & Ge, Yida & Wang, Zheng & Nazir, Muhammad Shahzad & Zhang, Chu, 2025. "An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction," Applied Energy, Elsevier, vol. 377(PD).
    7. Li, Qing & Zhang, Xinyan & Ma, Tianjiao & Jiao, Chunlei & Wang, Heng & Hu, Wei, 2021. "A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine," Energy, Elsevier, vol. 224(C).
    8. Gao, Xifeng & Zang, Yuesong & Ma, Qian & Liu, Mengmeng & Cui, Yiming & Dang, Dazhi, 2025. "A physics-constrained deep learning framework enhanced with signal decomposition for accurate short-term photovoltaic power generation forecasting," Energy, Elsevier, vol. 326(C).
    9. Liu, Jincheng & Li, Teng, 2024. "Multi-step power forecasting for regional photovoltaic plants based on ITDE-GAT model," Energy, Elsevier, vol. 293(C).
    10. Wang, Lining & Mao, Mingxuan & Xie, Jili & Liao, Zheng & Zhang, Hao & Li, Huanxin, 2023. "Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model," Energy, Elsevier, vol. 262(PB).
    11. Shi, Chaojun & Su, Zibo & Zhang, Ke & Xie, Xiongbin & Zhang, Xiaoyun, 2024. "CloudSwinNet: A hybrid CNN-transformer framework for ground-based cloud images fine-grained segmentation," Energy, Elsevier, vol. 309(C).
    12. Zhen, Hao & Niu, Dongxiao & Wang, Keke & Shi, Yucheng & Ji, Zhengsen & Xu, Xiaomin, 2021. "Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information," Energy, Elsevier, vol. 231(C).
    13. Zhai, Chao & He, Xinyi & Cao, Zhixiang & Abdou-Tankari, Mahamadou & Wang, Yi & Zhang, Minghao, 2025. "Photovoltaic power forecasting based on VMD-SSA-Transformer: Multidimensional analysis of dataset length, weather mutation and forecast accuracy," Energy, Elsevier, vol. 324(C).
    14. Li, Ruohan & Wang, Dongdong & Wang, Zhihao & Liang, Shunlin & Li, Zhanqing & Xie, Yiqun & He, Jiena, 2025. "Transformer approach to nowcasting solar energy using geostationary satellite data," Applied Energy, Elsevier, vol. 377(PA).
    15. Rai, Amit & Shrivastava, Ashish & Jana, Kartick C., 2023. "Differential attention net: Multi-directed differential attention based hybrid deep learning model for solar power forecasting," Energy, Elsevier, vol. 263(PC).
    16. Wang, Xiaoyang & Sun, Yunlin & Luo, Duo & Peng, Jinqing, 2022. "Comparative study of machine learning approaches for predicting short-term photovoltaic power output based on weather type classification," Energy, Elsevier, vol. 240(C).
    17. Zhu, Jianhua & He, Yaoyao, 2025. "A novel hybrid model based on evolving multi-quantile long and short-term memory neural network for ultra-short-term probabilistic forecasting of photovoltaic power," Applied Energy, Elsevier, vol. 377(PC).
    18. Wang, Xinyu & Ma, Wenping, 2024. "A hybrid deep learning model with an optimal strategy based on improved VMD and transformer for short-term photovoltaic power forecasting," Energy, Elsevier, vol. 295(C).
    19. Weyll, Arthur Lúcide Cotta & Kitagawa, Yasmin Kaore Lago & Araujo, Mirella Lima Saraiva & Ramos, Diogo Nunes da Silva & Lima, Francisco José Lopes de & Santos, Thalyta Soares dos & Jacondino, William , 2024. "Medium-term forecasting of global horizontal solar radiation in Brazil using machine learning-based methods," Energy, Elsevier, vol. 300(C).
    20. Zhang, Mingyue & Han, Yang & Wang, Chaoyang & Yang, Ping & Wang, Congling & Zalhaf, Amr S., 2024. "Ultra-short-term photovoltaic power prediction based on similar day clustering and temporal convolutional network with bidirectional long short-term memory model: A case study using DKASC data," Applied Energy, Elsevier, vol. 375(C).
    21. Tang, Huadu & Kang, Fei & Li, Xinyu & Sun, Yong, 2025. "Short-term photovoltaic power prediction model based on feature construction and improved transformer," Energy, Elsevier, vol. 320(C).
    22. Gong, Jianqiang & Qu, Zhiguo & Zhu, Zhenle & Xu, Hongtao, 2025. "Parallel TimesNet-BiLSTM model for ultra-short-term photovoltaic power forecasting using STL decomposition and auto-tuning," Energy, Elsevier, vol. 320(C).
    23. Guo, Hongxia & Chen, Lingxuan & Wang, Zhaocai & Li, Lin, 2025. "Day-ahead prediction of electric vehicle charging demand based on quadratic decomposition and dual attention mechanisms," Applied Energy, Elsevier, vol. 381(C).
    24. liu, Qian & li, Yulin & jiang, Hang & chen, Yilin & zhang, Jiang, 2024. "Short-term photovoltaic power forecasting based on multiple mode decomposition and parallel bidirectional long short term combined with convolutional neural networks," Energy, Elsevier, vol. 286(C).
    25. Wang, Tao & Xu, Ye & Qin, Yu & Wang, Xu & Zheng, Feifan & Li, Wei, 2025. "Short-term PV forecasting of multiple scenarios based on multi-dimensional clustering and hybrid transformer-BiLSTM with ECPO," Energy, Elsevier, vol. 334(C).
    26. Hu, Zehuan & Gao, Yuan & Ji, Siyu & Mae, Masayuki & Imaizumi, Taiji, 2024. "Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data," Applied Energy, Elsevier, vol. 359(C).
    27. Khan, Zulfiqar Ahmad & Hussain, Tanveer & Baik, Sung Wook, 2023. "Dual stream network with attention mechanism for photovoltaic power forecasting," Applied Energy, Elsevier, vol. 338(C).
    28. Lin, Huapeng & Gao, Liyuan & Cui, Mingtao & Liu, Hengchao & Li, Chunyang & Yu, Miao, 2025. "Short-term distributed photovoltaic power prediction based on temporal self-attention mechanism and advanced signal decomposition techniques with feature fusion," Energy, Elsevier, vol. 315(C).
    29. Ma, Yifeng & Yu, Wenzheng & Zhu, Junyu & You, Zhiyuan & Jia, Aiqing, 2025. "Research on ultra-short-term photovoltaic power forecasting using multimodal data and ensemble learning," Energy, Elsevier, vol. 330(C).
    30. Chen, Xiang & Ding, Kun & Zhang, Jingwei & Han, Wei & Liu, Yongjie & Yang, Zenan & Weng, Shuai, 2022. "Online prediction of ultra-short-term photovoltaic power using chaotic characteristic analysis, improved PSO and KELM," Energy, Elsevier, vol. 248(C).
    31. Jia, Dongyu & Yang, Liwei & Lv, Tao & Liu, Weiping & Gao, Xiaoqing & Zhou, Jiaxin, 2022. "Evaluation of machine learning models for predicting daily global and diffuse solar radiation under different weather/pollution conditions," Renewable Energy, Elsevier, vol. 187(C), pages 896-906.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wang, Tao & Xu, Ye & Qin, Yu & Wang, Xu & Zheng, Feifan & Li, Wei, 2025. "Short-term PV forecasting of multiple scenarios based on multi-dimensional clustering and hybrid transformer-BiLSTM with ECPO," Energy, Elsevier, vol. 334(C).
    2. Tian, Zhirui & Liang, Bingjie, 2025. "PVMTF: End-to-end long-sequence time-series forecasting frameworks based on patch technique and information fusion coding for mid-term photovoltaic power forecasting," Applied Energy, Elsevier, vol. 396(C).
    3. Li, Jiaqian & Rao, Congjun & Gao, Mingyun & Xiao, Xinping & Goh, Mark, 2025. "Efficient calculation of distributed photovoltaic power generation power prediction via deep learning," Renewable Energy, Elsevier, vol. 246(C).
    4. Zheng, Feifan & Li, Zhongyan & Xu, Ye & Li, Wei & Wang, Tao, 2026. "A hybrid prediction model of photovoltaic power system based on AP, ISSA-based VMD, CLKAN and error correction," Renewable and Sustainable Energy Reviews, Elsevier, vol. 226(PC).
    5. Gong, Jianqiang & Qu, Zhiguo & Zhu, Zhenle & Xu, Hongtao, 2025. "Parallel TimesNet-BiLSTM model for ultra-short-term photovoltaic power forecasting using STL decomposition and auto-tuning," Energy, Elsevier, vol. 320(C).
    6. Yang, Mao & Jiang, Yue & Guo, Yunfeng & Su, Xin & Li, Yi & Huang, Tao, 2025. "Ultra-short-term prediction of photovoltaic cluster power based on spatiotemporal convergence effect and spatiotemporal dynamic graph attention network," Renewable Energy, Elsevier, vol. 255(C).
    7. Yang, Shaomei & Luo, Yuman, 2025. "Short-term photovoltaic power prediction based on RF-SGMD-GWO-BiLSTM hybrid models," Energy, Elsevier, vol. 316(C).
    8. Zhai, Chao & He, Xinyi & Cao, Zhixiang & Abdou-Tankari, Mahamadou & Wang, Yi & Zhang, Minghao, 2025. "Photovoltaic power forecasting based on VMD-SSA-Transformer: Multidimensional analysis of dataset length, weather mutation and forecast accuracy," Energy, Elsevier, vol. 324(C).
    9. Lin, Huapeng & Gao, Liyuan & Cui, Mingtao & Liu, Hengchao & Li, Chunyang & Yu, Miao, 2025. "Short-term distributed photovoltaic power prediction based on temporal self-attention mechanism and advanced signal decomposition techniques with feature fusion," Energy, Elsevier, vol. 315(C).
    10. Ridha, Hussein Mohammed & Ahmadipour, Masoud & Alghrairi, Mokhalad & Hizam, Hashim & Mirjalili, Seyedali & Zubaidi, Salah L. & Mohammed S, Marwa Y., 2026. "A novel hybrid photovoltaic current prediction model utilizing singular spectrum analysis, adaptive beluga whale optimization, and improved extreme learning machine," Renewable Energy, Elsevier, vol. 256(PA).
    11. Gao, Xifeng & Zang, Yuesong & Ma, Qian & Liu, Mengmeng & Cui, Yiming & Dang, Dazhi, 2025. "A physics-constrained deep learning framework enhanced with signal decomposition for accurate short-term photovoltaic power generation forecasting," Energy, Elsevier, vol. 326(C).
    12. Hong Wu & Haipeng Liu & Huaiping Jin & Yanping He, 2024. "Ultra-Short-Term Photovoltaic Power Prediction by NRGA-BiLSTM Considering Seasonality and Periodicity of Data," Energies, MDPI, vol. 17(18), pages 1-19, September.
    13. Hao, Jianhua & Liu, Fangai & Zhang, Weiwei, 2024. "Multi-scale RWKV with 2-dimensional temporal convolutional network for short-term photovoltaic power forecasting," Energy, Elsevier, vol. 309(C).
    14. Wan, Hang & Wang, Jiasong & Gan, Quan & Xia, Yaping & Chang, Yufang & Yan, Huaicheng, 2025. "Addressing intermittency in medium-term photovoltaic and wind power forecasting using a hybrid xLSTM-TCCNN model with numerical weather predictions," Renewable Energy, Elsevier, vol. 253(C).
    15. Huang, Congzhi & Yang, Mengyuan, 2023. "Memory long and short term time series network for ultra-short-term photovoltaic power forecasting," Energy, Elsevier, vol. 279(C).
    16. Yu, Weijie & Dai, Yeming & Wang, Wenjie & Ren, Tao & Leng, Mingming, 2026. "Short-term photovoltaic forecasting: A parallel TimesNet and AT-Informer-AT method," Renewable Energy, Elsevier, vol. 258(C).
    17. Luo, Ping & Li, Chenlei & Kang, Dongming & Zhang, Fan & Lv, Qiang, 2026. "PMWC: A hybrid framework based causal inference and multi-scale feature fusion for day-ahead PV power forecasting," Renewable Energy, Elsevier, vol. 257(C).
    18. Zhu, Honglu & Wang, Yuhang & Wu, Ji & Zhang, Xi, 2026. "A regional distributed photovoltaic power generation forecasting method based on grid division and TCN-Bilstm," Renewable Energy, Elsevier, vol. 256(PA).
    19. Wang, Jianing & Gao, Shan & Zhao, Xin & Huang, Xueliang & Lu, Jianyu & Wu, Chuanshen, 2025. "A cross-domain information fusion method for non-stationary distributed photovoltaic forecasting," Applied Energy, Elsevier, vol. 402(PA).
    20. Song, Enzhe & Zhang, Xinyue & Ge, Yuwei & Yao, Chong & Wang, Bo, 2025. "Parallel TCN-BiGRU architecture with dynamic attention for ship energy consumption prediction under variable navigation conditions," Energy, Elsevier, vol. 337(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:347:y:2026:i:c:s0360544226004172. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.