电力系统自动化2026，Vol.50Issue(7)：218-231,14.DOI:10.7500/AEPS20250609010
基于时空特征自适应提取与状态转移融合的表后光伏分解方法
Behind-the-meter Photovoltaic Disaggregation Method Based on Adaptive Extraction and State Transition Fusion of Spatiotemporal Features
摘要
Abstract
With the advancement of the"Thousands of Households Embracing Sunlight Initiative",an increasing number of distributed photovoltaic(PV)installations are being placed behind smart meters.Their unobservable nature poses significant challenges to distribution network planning and operation,highlighting an urgent need for accurate and reliable methods for behind-the-meter PV disaggregation.However,existing disaggregation methods remain inadequate in extracting and deeply integrating periodic temporal features and spatial correlation features.To address this issue,this paper proposes a behind-the-meter PV disaggregation method based on adaptive extraction and state transition fusion of spatiotemporal features.First,an adaptive adjacency matrix is constructed to dynamically characterize the spatial correlations among users,mapping net load data into a dynamic spatiotemporal graph structure.Second,the net load data is periodically decoupled by integrating time-domain and frequency-domain information,enabling the extraction and aggregation of multi-scale periodic features.Subsequently,graph diffusion convolutional neural networks are employed in the spatial dimension to extract wide-area spatial features.Finally,a selective spatiotemporal state model based on dynamic spatiotemporal graph embedding is used to deeply integrate the spatiotemporal features and generate behind-the-meter PV disaggregation results.Experimental results on a real-world dataset comprising 268 users demonstrate that the proposed method reduces the mean absolute error by 58.8%compared to existing disaggregation methods.Even under a metering data missing rate of up to 15%,the error is reduced by at least 61.7%.关键词
光伏分解/动态时空图/时空特征/状态转移/图扩散卷积神经网络/选择性时空状态模型Key words
photovoltaic disaggregation/dynamic spatiotemporal graph/spatiotemporal feature/state transition/graph diffusion convolutional neural network/selective spatiotemporal state model引用本文复制引用
张桦晖,罗庆全,余涛,胡小磊,王克英,潘振宁..基于时空特征自适应提取与状态转移融合的表后光伏分解方法[J].电力系统自动化,2026,50(7):218-231,14.基金项目
国家自然科学基金企业创新发展联合基金集成项目(U24B6010) （U24B6010）
广东省基础与应用基础研究基金资助项目(2025A1515010118). This work is supported by National Natural Science Foundation of China(No.U24B6010)and Guangdong Provincial Basic and Applied Basic Research Foundation of China(No.2025A1515010118). （2025A1515010118）
