RR4WindEnergy

A practical example of reproducible research in wind energy, using publicly available data from Kelmarsh wind farm and the methodology of Sopena (2023).

Project Structure

RR4WindEnergy/
├── src/
│   └── rr4we/              # Main package
│       ├── data/           # Data preprocessing utilities
│       ├── models/         # Neural network models
│       ├── utils/          # Utility functions and metrics
│       └── vmd/            # Variational Mode Decomposition
├── notebooks/              # Jupyter notebooks
│   ├── 01_data_preprocessing.ipynb
│   ├── 02_generate_vmd_datasets.ipynb
│   └── 03_wind_power_forecast.ipynb
├── data/
│   ├── raw/                # Raw SCADA data
│   └── processed/          # Processed data files
├── results/                # Model outputs and predictions
├── figures/                # Generated plots and visualizations
└── tests/                  # Unit tests

Installation

1. Clone the repository:

git clone <repository-url>
cd RR4WindEnergy

2. Create a virtual environment (recommended):

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the package:

pip install -e .

Or install dependencies directly:

pip install -r requirements.txt

Usage

1. Data Preprocessing

Run the data preprocessing notebook to load and clean the raw SCADA data:

jupyter notebook notebooks/01_data_preprocessing.ipynb

2. Generate VMD Datasets

Decompose the time series data using Variational Mode Decomposition:

jupyter notebook notebooks/02_generate_vmd_datasets.ipynb

3. Train Models and Forecast

Train neural network models and generate forecasts:

jupyter notebook notebooks/03_wind_power_forecast.ipynb

Dependencies

numpy pandas scipy scikit-learn tensorflow matplotlib python-dateutil jupyter ipykernel notebook

See requirements.txt for the complete list of dependencies.

Citation

If you use this code, please cite the original paper:

Sopena, J. G. (2023). A benchmarking framework for performance evaluation of statistical wind power forecasting models. Sustainable Energy Technologies and Assessments, 103246. https://doi.org/10.1016/j.seta.2023.103246

License

See LICENSE file for details.