Measurement-Based Probabilistic Power Flow Using a Basis Constrained Graph Convolutional Network with Few-Shot Node Adaptation
Jinbao Wang, Jun Liu, Haobo Zhang, Bairen An, Chencong Zhao · 2026
Read Measurement-Based Probabilistic Power Flow Using a Basis Constrained Graph Convolutional Network with Few-Shot Node Adaptation by Jinbao Wang, Jun Liu, Haobo Zhang, Bairen An, Chencong Zhao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13568108.txt.
Description
Jinbao Wang, Jun Liu, Haobo Zhang, Bairen An, and Chencong Zhao propose a graph network for probabilistic power flow in a 2026 paper. Grid operators must quantify voltage uncertainty as solar output varies. Repeated simulation is costly, and adding a bus locally changes the network math when only little new data exist.
Their basis constrained network predicts corrections around a first order solution, using graph and mode information. Only rows for new buses are adapted while the backbone stays frozen. The method led on small grid expansions but won few cells on a large grid and none on a very large one, marking its scale limit.
Catalog record
| CREATOR | Jinbao Wang, Jun Liu, Haobo Zhang, Bairen An, Chencong Zhao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |