Attention‐LSTM‐Based Conditional Imputation for SCU Transformer Data
The Journal of Engineering · 2026-01 · 2026 (1)
DOI: 10.1049/tje2.70186 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Engineering, online erschienen am 16.07.2026. Verfasst von Xiaotong Ji und 7 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: State Grid Corporation of China.
Abstract (Originalsprache)
Data collected by smart converged units (SCUs) often suffers from missing values, severely impacting the monitoring and analysis of distribution network operations. Accurate imputation is thus essential to ensure data reliability. However, existing methods struggle with the high dimensionality, non‐smoothness, and complex missing patterns typical of PV station data, leading to poor imputation accuracy. To address this, we propose an attention‐LSTM‐based imputation method tailored to SCU station transformer data under varying operating conditions. First, data is grouped based on PV equipment operating states to reduce complexity. Then, HDBSCAN clustering is applied to further distinguish operating conditions, enhancing model adaptability. Finally, an attention‐LSTM model is used to learn temporal features within each condition for precise imputation. Simulation results demonstrate that the proposed approach effectively handles irregularities and missing data patterns, significantly improving both imputation accuracy and model generalization. This method offers a robust and efficient solution for data restoration in PV distribution networks.
Förderung
- State Grid Corporation of China
Zitieren
APA
Ji, X., Feng, B., Feng, W., Wei, M., Hu, Y., Hu, P., Su, L., & Cao, K. (2026). Attention‐LSTM‐Based Conditional Imputation for SCU Transformer Data. The Journal of Engineering, 2026(1). https://doi.org/10.1049/tje2.70186
Vancouver
Ji X, Feng B, Feng W, Wei M, Hu Y, Hu P, et al. Attention‐LSTM‐Based Conditional Imputation for SCU Transformer Data. The Journal of Engineering. 2026;2026(1). doi:10.1049/tje2.70186
BibTeX
@article{Ji2026,
author = {Ji, Xiaotong and Feng, Bingyang and Feng, Wanli and Wei, Mingjiang and Hu, Yuxuan and Hu, Pan and Su, Lei and Cao, Kan},
title = {Attention‐LSTM‐Based Conditional Imputation for SCU Transformer Data},
journal = {The Journal of Engineering},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1049/tje2.70186}
}
EUVIMED