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

Zhiheng Xu, Peidong Chen, Ran Cheng, Yao Duan, Qiang Luo, Huahui Zhang, Zhenning Pan and Wencong Xiao ()
Additional contact information
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

Energies, 2025, vol. 18, issue 19, 1-15

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.

Keywords: non-intrusive load monitoring; photovoltaic disaggregation; multi-scale modeling; multimodal fusion; time series representation (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/19/5271/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/19/5271/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:19:p:5271-:d:1764828

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().