IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i19p5271-d1764828.html

Photovoltaic Decomposition Method Based on Multi-Scale Modeling and Multi-Feature Fusion

Author

Listed:
  • Zhiheng Xu

    (Power System Planning Research Center of Guangdong Power Grid Co., Ltd., Guangzhou 510623, China)

  • Peidong Chen

    (Power System Planning Research Center of Guangdong Power Grid Co., Ltd., Guangzhou 510623, China)

  • Ran Cheng

    (Power System Planning Research Center of Guangdong Power Grid Co., Ltd., Guangzhou 510623, China)

  • Yao Duan

    (Power System Planning Research Center of Guangdong Power Grid Co., Ltd., Guangzhou 510623, China)

  • Qiang Luo

    (Power System Planning Research Center of Guangdong Power Grid Co., Ltd., Guangzhou 510623, China)

  • Huahui Zhang

    (School of Electric Power Engineering, South China University of Technology, Guangzhou 510641, China)

  • Zhenning Pan

    (School of Electric Power Engineering, South China University of Technology, Guangzhou 510641, China)

  • Wencong Xiao

    (School of Electric Power Engineering, South China University of Technology, Guangzhou 510641, China)

Abstract

Deep learning-based Non-Intrusive Load Monitoring (NILM) methods have been widely applied to residential load identification. However, photovoltaic (PV) loads exhibit strong non-stationarity, high dependence on weather conditions, and strong coupling with multi-source data, which limit the accuracy and generalization of existing models. To address these challenges, this paper proposes a multi-scale and multi-feature fusion framework for PV disaggregation, consisting of three modules: Multi-Scale Time Series Decomposition (MTD), Multi-Feature Fusion (MFF), and Temporal Attention Decomposition (TAD). These modules jointly capture short-term fluctuations, long-term trends, and deep dependencies across multi-source features. Experiments were conducted on real residential datasets from southern China. Results show that, compared with representative baselines such as SGN-Conv and MAT-Conv, the proposed method reduces MAE by over 60% and SAE by nearly 70% for some users, and it achieves more than 45% error reduction in cross-user tests. These findings demonstrate that the proposed approach significantly enhances both accuracy and generalization in PV load disaggregation.

Suggested Citation

  • Zhiheng Xu & Peidong Chen & Ran Cheng & Yao Duan & Qiang Luo & Huahui Zhang & Zhenning Pan & Wencong Xiao, 2025. "Photovoltaic Decomposition Method Based on Multi-Scale Modeling and Multi-Feature Fusion," Energies, MDPI, vol. 18(19), pages 1-15, October.
    • Handle: RePEc:gam:jeners:v:18:y:2025:i:19:p:5271-:d:1764828
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/19/5271/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/18/19/5271/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Georgios Tsoumplekas & Christos Athanasiadis & Dimitrios I. Doukas & Antonios Chrysopoulos & Pericles Mitkas, 2025. "Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach," Energies, MDPI, vol. 18(3), pages 1-23, February.
    2. 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).
    3. Silvia Moreno & Hector Teran & Reynaldo Villarreal & Yolanda Vega-Sampayo & Jheifer Paez & Carlos Ochoa & Carlos Alejandro Espejo & Sindy Chamorro-Solano & Camilo Montoya, 2024. "An Ensemble Method for Non-Intrusive Load Monitoring (NILM) Applied to Deep Learning Approaches," Energies, MDPI, vol. 17(18), pages 1-11, September.
    4. İsmail Hakkı Çavdar & Vahit Feryad, 2021. "Efficient Design of Energy Disaggregation Model with BERT-NILM Trained by AdaX Optimization Method for Smart Grid," Energies, MDPI, vol. 14(15), pages 1-21, July.
    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. Zhang, Zongbin & Huang, Xiaoqiao & Li, Chengli & Cheng, Feiyan & Tai, Yonghang, 2025. "CRAformer: A cross-residual attention transformer for solar irradiation multistep forecasting," Energy, Elsevier, vol. 320(C).
    2. 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).
    3. Yingjie Liu & Mao Yang, 2025. "Ultra-Short-Term Photovoltaic Power Prediction Based on Predictable Component Reconstruction and Spatiotemporal Heterogeneous Graph Neural Networks," Energies, MDPI, vol. 18(15), pages 1-30, August.
    4. 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).
    5. Li, Jingtao & Ren, Xiaoying & Zhang, Fei & Gao, Lu & Li, Jierui & Cui, Tonghe, 2025. "Multi-timescale photovoltaic station power prediction based on Reformer model," Energy, Elsevier, vol. 327(C).
    6. Song, Shihao & Meng, Anbo & Tan, Zhenglin & Lu, Jiajun & Xiao, Liexi & Yin, Hao & Luo, Jianqiang, 2026. "Dynamic graph convolutional network considering wind speed delay and two-stage transfer learning applied to few-shot wind power prediction," Energy, Elsevier, vol. 342(C).
    7. Song, Shihao & Meng, Anbo & Xiao, Liexi & Tan, Zhenglin & Zou, Pengli & Yin, Hao & Luo, Jianqiang, 2025. "Research on data augmentation and synthetic sample quantity uncertainty in few-shot wind power prediction based on the adaptive CRITIC-HLICRVFL method," Renewable Energy, Elsevier, vol. 252(C).
    8. Yeji Lim & Minjae Son & Kyungnam Park & Minsoo Kim & Keunju Song & Haejoong Lee & Hongseok Kim, 2025. "Power System Decision Making in the Age of Deep Learning: A Comprehensive Review," Energies, MDPI, vol. 18(18), pages 1-49, September.
    9. Zhang, Xinyu & Zhang, Chu & He, Rui & Ma, Changwen & Yao, Junhao & Nazir, Muhammad Shahzad & Peng, Tian, 2025. "A pyramidal attention-based transformer model based on improved differential innovation search algorithm and feature extraction for solar radiation prediction considering relevant factors," Renewable Energy, Elsevier, vol. 253(C).
    10. He, Rui & Peng, Tian & Zhang, Xinyu & Chen, Zhigang & Yao, Junhao & Nazir, Muhammad Shahzad & Zhang, Chu, 2026. "A novel hybrid model for state of health prediction in lithium batteries based on non-stationary transformers optimized by tree-structured Parzen estimator considering health factors," Applied Energy, Elsevier, vol. 402(PC).

    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:gam:jeners:v:18:y:2025:i:19:p:5271-:d:1764828. 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: MDPI Indexing Manager The email address of this maintainer does not seem to be valid anymore. Please ask MDPI Indexing Manager to update the entry or send us the correct address (email available below). General contact details of provider: https://www.mdpi.com .

    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.