A Latent Diffusion-Enhanced Spatio-Temporal Transformer for Short-Term Smart Grid Traffic Prediction
Energies · 15.06.2026 · 19 (12) · 2843
DOI: 10.3390/en19122843 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 15.06.2026. Verfasst von Haitong Gu und 8 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of China Southern Power Grid Co., Ltd..
Abstract (Originalsprache)
Accurate short-term prediction of network service traffic is essential for communication resource allocation and proactive fault warning in smart grids. However, smart grid service traffic is characterized by nonlinear fluctuations, strong spatio-temporal coupling, and considerable uncertainty, making it difficult for existing methods to capture long-range dependencies, adapt to dynamic topological relationships, and reflect prediction risks. To address these issues, this work develops a deep learning framework that integrates a spatio-temporal Transformer with a diffusion mechanism. The spatio-temporal Transformer extracts temporal evolution patterns and spatial logical correlations from historical traffic matrices, while the diffusion module improves robustness to abrupt traffic variations through latent uncertainty modeling. Furthermore, attention-guided recurrent units are used to generate stable multi-step forecasting sequences. Experiments on a real-world network dataset show that, compared with mainstream benchmark models, the proposed framework reduces Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Root Relative Squared Error (RRSE) by 46.62%, 47.05%, and 44.18%, respectively. These results indicate that the framework improves prediction accuracy and stability while alleviating error accumulation in long-horizon forecasting, thereby providing reliable technical support for smart grid network management.
Förderung
- Science and Technology Project of China Southern Power Grid Co., Ltd.
Zitieren
APA
Gu, H., Guo, B., Dong, J., Feng, X., Wu, X., Liang, C., Lin, J., Wang, W., & Guan, Q. (2026). A Latent Diffusion-Enhanced Spatio-Temporal Transformer for Short-Term Smart Grid Traffic Prediction. Energies, 19(12), 2843. https://doi.org/10.3390/en19122843
Vancouver
Gu H, Guo B, Dong J, Feng X, Wu X, Liang C, et al. A Latent Diffusion-Enhanced Spatio-Temporal Transformer for Short-Term Smart Grid Traffic Prediction. Energies. 2026;19(12):2843. doi:10.3390/en19122843
BibTeX
@article{Gu2026,
author = {Gu, Haitong and Guo, Bin and Dong, Jun and Feng, Xingxing and Wu, Xiaoqiang and Liang, Chaoheng and Lin, Jingbo and Wang, Weidong and Guan, Quansheng},
title = {A Latent Diffusion-Enhanced Spatio-Temporal Transformer for Short-Term Smart Grid Traffic Prediction},
journal = {Energies},
year = {2026},
volume = {19},
number = {12},
pages = {2843},
doi = {10.3390/en19122843}
}
EUVIMED