Python Notebook for Neural Network

All files end in .ipynb are Python notebook files. These files are needed to build the neural network based power flow model. Additional python libraries are required to run these notebook files: pytorch, numpy, matplotlib, csv.

Generated data files for training Neural Network

All data files are stored in .csv format. The datat set contains training data for different IEEE systems. Using data_x_pf_9 as an example, each column is a data sample.

• The first 9 rows are active power (1-9).
• The second 9 rows are reactive power(10-18).
• The third 9 rows are initial voltage (19-27).

MATLAB files to generate data

If you want to create your own data set, the .m files will generate your own training data set. MATLAB software and Matpower toolbox are needed in order to run these files.

Contributions:

This work was conducted by Thuan Pham. Xingpeng Li supervised this work.

Contact:

Thuan Pham

University of Houston

Email: tdpham7@cougarnet.uh.edu

Website: https://rpglab.github.io/people/Thuan-Pham/

Datasets:

The datasets are available on Figshare. The link is as follows: https://figshare.com/articles/dataset/Generated_Data_for_Different_Systems/19427006/2

Citation:

If you use these codes for your work, please cite the following paper:

Thuan Pham and Xingpeng Li, “Neural Network-based Power Flow Model”, IEEE Green Technologies Conference, Houston, TX, USA, Mar. 2022. https://doi.org/10.1109/GreenTech52845.2022.9772026

Paper website: https://rpglab.github.io/papers/ThuanP-NN-PF/

License:

This work is licensed under the terms of the Creative Commons Attribution 4.0 (CC BY 4.0) license.

Disclaimer:

The author doesn’t make any warranty for the accuracy, completeness, or usefulness of any information disclosed and the author assumes no liability or responsibility for any errors or omissions for the information (data/code/results etc) disclosed.