Wind Energy Analysis and Forecasting

Project Title: Wind Energy Analysis and Forecasting

GitHub Repository: Link

Tools: Python, Pandas, Numpy, Matplotlib, Seaborn, Time, Windrose, LSTM,Keras

Approach:

1. Performed EDA

2. Created Plots to visualize Data

3. Utilized an LSTM (Long Short-Term Memory) neural network for forecasting.

4. Performed Model Evaluation with a Mean Absolute Percent Error of 0.4612.

Visualizations:

1. Wind direction vs Wind Speed

2. KDE Plot

3. Final Prediction Plot

Conclusion:

The project successfully implemented an LSTM-based forecasting model for predicting and forecasting the power generated by wind turbines. The model's performance was evaluated using MAPE, and the results were visualized to provide insights into power generation trends