This is the Github repository for National Wind Database Task 3! T3 uses machine learning algorithms to provide stochastic power curve modeling.

NOTE: The installation instruction below assume that you have python installed on your machine and are using conda as your package/environment manager.

1. Create a new environment: conda create --name nwdbt3 python=3.8
2. Activate environment: conda activate nwdbt3
3. Install packages listed in rq.txt

1. manupc_cleaning.py cleans the raw data in Data/All/.
   Example of data cleaning.
   
2. ANN_trainging.ipynb trains the model for a single turbine.
   Example of wind turbine uncertainty modeling.
   
3. ProbMetrics_2.R calcualates the metrics for wind turbine uncertainty quantification.
4. Analysis_SPC_WindRegion.R outputs the relialibility and sharpness plots.
   

  Example of reliability plot.          Example of sharpness plot.

Please check back in the future

Funding provided by the DOE Wind Energy Technologies Office (WETO).