Parameter-Efficient Domain Adaptation of Physics-Informed Self-Attention based GNNs for AC Power Flow Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916019410305024 |
|---|---|
| author | Karim, Redwanul Kim, Changhun Conrad, Timon Gourmelon, Nora Oelhaf, Julian Riebesel, David Arias-Vergara, Tomás Maier, Andreas Jäger, Johann Bayer, Siming |
| author_facet | Karim, Redwanul Kim, Changhun Conrad, Timon Gourmelon, Nora Oelhaf, Julian Riebesel, David Arias-Vergara, Tomás Maier, Andreas Jäger, Johann Bayer, Siming |
| contents | Accurate AC power flow (AC-PF) prediction under domain shift is critical when models trained on medium-voltage (MV) grids are deployed on high-voltage (HV) networks. Existing physics-informed graph neural network (GNN) solvers typically rely on full fine-tuning for cross-regime transfer, incurring high retraining cost and offering limited control over the stability-plasticity trade-off between target-domain adaptation and source-domain retention. We study parameter-efficient domain adaptation for physics-informed self-attention-based GNNs, encouraging Kirchhoff-consistent behavior via a physics-based loss while restricting adaptation to low-rank updates. Specifically, we apply low-rank adaptation (LoRA) to attention projections with selective unfreezing of the prediction head to regulate adaptation capacity. This design yields a controllable efficiency-accuracy trade-off for physics-constrained inverse estimation under voltage-regime shift. Across multiple grid topologies, the proposed LoRA+PHead adaptation recovers near-full fine-tuning accuracy with a target-domain RMSE gap of $2.6 \times 10^{-4}$ while reducing the number of trainable parameters by $85.46\%$. The physics-based residual remains comparable to full fine-tuning; however, relative to Full FT, LoRA+PHead reduces MV source retention by 4.7 percentage points (17.9% vs. 22.6%) under domain shift, while still enabling parameter-efficient and physically consistent AC-PF estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18227 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Parameter-Efficient Domain Adaptation of Physics-Informed Self-Attention based GNNs for AC Power Flow Prediction Karim, Redwanul Kim, Changhun Conrad, Timon Gourmelon, Nora Oelhaf, Julian Riebesel, David Arias-Vergara, Tomás Maier, Andreas Jäger, Johann Bayer, Siming Machine Learning Accurate AC power flow (AC-PF) prediction under domain shift is critical when models trained on medium-voltage (MV) grids are deployed on high-voltage (HV) networks. Existing physics-informed graph neural network (GNN) solvers typically rely on full fine-tuning for cross-regime transfer, incurring high retraining cost and offering limited control over the stability-plasticity trade-off between target-domain adaptation and source-domain retention. We study parameter-efficient domain adaptation for physics-informed self-attention-based GNNs, encouraging Kirchhoff-consistent behavior via a physics-based loss while restricting adaptation to low-rank updates. Specifically, we apply low-rank adaptation (LoRA) to attention projections with selective unfreezing of the prediction head to regulate adaptation capacity. This design yields a controllable efficiency-accuracy trade-off for physics-constrained inverse estimation under voltage-regime shift. Across multiple grid topologies, the proposed LoRA+PHead adaptation recovers near-full fine-tuning accuracy with a target-domain RMSE gap of $2.6 \times 10^{-4}$ while reducing the number of trainable parameters by $85.46\%$. The physics-based residual remains comparable to full fine-tuning; however, relative to Full FT, LoRA+PHead reduces MV source retention by 4.7 percentage points (17.9% vs. 22.6%) under domain shift, while still enabling parameter-efficient and physically consistent AC-PF estimation. |
| title | Parameter-Efficient Domain Adaptation of Physics-Informed Self-Attention based GNNs for AC Power Flow Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.18227 |