🔥 FHEC

A method combined federated learning and deep learning for household energy consumption forecasting.

📚 Requirements

Dependent libraries are placed in a file named 'requirements.txt'. Requirements(Briefly):
python==3.7.8
tensorflow==2.3.1
torch==1.7.1
torchvision==0.8.2
torchaudio==0.7.2
pandas
matplotlib
scikit-learn

📒 Usage

1. Run 'Center.py' in Server. Run 'Node-x.py' in Client-x.
2. Modify the corresponding 'host' and 'port' code case by case.

🌟 Citation

If you find our repo useful for your research, please consider giving a 🌟 and citing our work below.

@article{JIN2022101442,
title = {Highly accurate energy consumption forecasting model based on parallel LSTM neural networks},
journal = {Advanced Engineering Informatics},
volume = {51},
pages = {101442},
year = {2022},
issn = {1474-0346},
doi = {https://doi.org/10.1016/j.aei.2021.101442},
url = {https://www.sciencedirect.com/science/article/pii/S1474034621001944},
author = {Ning Jin and Fan Yang and Yuchang Mo and Yongkang Zeng and Xiaokang Zhou and Ke Yan and Xiang Ma}
}

@article{YANG2023101846,
title = {Multiple households energy consumption forecasting using consistent modeling with privacy preservation},
journal = {Advanced Engineering Informatics},
volume = {55},
pages = {101846},
year = {2023},
issn = {1474-0346},
doi = {https://doi.org/10.1016/j.aei.2022.101846},
url = {https://www.sciencedirect.com/science/article/pii/S1474034622003044},
author = {Fan Yang and Ke Yan and Ning Jin and Yang Du}
}

🔐 License

The source code is free for research and education use only. Any commercial use should get formal permission first.