Wind Speed Forecasting using Deep Learning

Wind energy is a resource that is environmentally sustainable, crucial component needed for wind energy production. Accurate estimation of wind speed is essential for many applications. This paper proposes the Hybrid deep learning model for wind speed forecasting. The hybrid wind speed model was developed based on the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). CNN model includes a series of Convolutional layers followed by pooling layers, designed to extract relevant features from the input sequences, final dense layers of the network facilitate the prediction of future wind speeds. LSTM model is used for improving the accuracy of short - term prediction. Using the wind dataset from the National Renewable Energy Laboratory (NREL) in Muppandal, Kanyakumari, Tamil Nadu, wind speed was determined. The performance of the proposed model (CNN-LSTM) is quantified using Mean Absolute Error (MAE), Mean Root Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The experimental results proved that the proposed hybrid model outperformed the benchmarks models being the RNN, CNN, GRU and LSTM.