mukhlishga/gnn-powerflow
Graph Neural Network application in predicting AC Power Flow calculation. Developed with Pytorch Geometric framework. My Master Thesis at Eindhoven University of Technology
This project helps power systems engineers analyze the flow of electricity by predicting unknown electrical variables across a power grid. It takes the known variables and the grid's physical connections (like buses and lines) as input. The output is a prediction of the remaining electrical quantities, such as voltage or reactive power, offering a data-driven alternative to traditional power flow calculations. It's designed for professionals involved in power system planning, operations, or research.
110 stars. No commits in the last 6 months.
Use this if you need to predict complex power flow outcomes in an electrical grid by leveraging both the electrical measurements and the physical topology of the network.
Not ideal if your power system data lacks clear graph-like structures or if you require solely physics-based, non-ML power flow solutions.
Stars
110
Forks
20
Language
Jupyter Notebook
License
—
Category
Last pushed
May 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mukhlishga/gnn-powerflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.