Physics-Informed Graph Attention Network with Topology Masking for Probabilistic Load Forecasting in Active Distribution Networks
Energies · 04.03.2026 · 19 (5) · 1294
DOI: 10.3390/en19051294 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 04.03.2026. Verfasst von Wenting Lei und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Sichuan Electric Power Company Science and Technology.
Abstract (Originalsprache)
The integration of distributed photovoltaics (PV) introduces time-varying electrical coupling in active distribution networks, limiting the efficacy of conventional forecasting methods that rely on incomplete topological information and static physical models. This paper proposes a physics-informed spatio-temporal graph attention network (PI-STGAT) for probabilistic load forecasting under highly fluctuating conditions. A condition-adaptive correlation blending mechanism, derived from voltage–power sensitivity principles, fuses physical priors with statistical correlations using a PV-weighted strategy to capture time-varying electrical connectivity. An impedance-weighted continuous physical gating architecture maps voltage correlation coefficients into continuous attention biases, reflecting the spatial continuity of electrical distances while suppressing long-range noise. An uncertainty-aware adaptive physical constraint strategy dynamically modulates physical loss weights based on prediction variance and PV penetration, balancing fitting accuracy against physical consistency. Validation on real-world distribution network data demonstrates that, over a 24 h day-ahead horizon, PI-STGAT achieves a MAPE of 5.50%, a 3.7% relative reduction compared with LSTM. The model further attains a prediction interval coverage probability of 97.9%, confirming reliable uncertainty estimates under complex conditions.
Förderung
- State Grid Sichuan Electric Power Company Science and Technology
Zitieren
APA
Lei, W., Peng, W., Dai, C., & Dong, S. (2026). Physics-Informed Graph Attention Network with Topology Masking for Probabilistic Load Forecasting in Active Distribution Networks. Energies, 19(5), 1294. https://doi.org/10.3390/en19051294
Vancouver
Lei W, Peng W, Dai C, Dong S. Physics-Informed Graph Attention Network with Topology Masking for Probabilistic Load Forecasting in Active Distribution Networks. Energies. 2026;19(5):1294. doi:10.3390/en19051294
BibTeX
@article{Lei2026,
author = {Lei, Wenting and Peng, Weifeng and Dai, Chenxi and Dong, Shufeng},
title = {Physics-Informed Graph Attention Network with Topology Masking for Probabilistic Load Forecasting in Active Distribution Networks},
journal = {Energies},
year = {2026},
volume = {19},
number = {5},
pages = {1294},
doi = {10.3390/en19051294}
}
EUVIMED