SHORT-TERM WIND SPEED FORECASTING USING DEEP VARIATIONAL LSTM

Abstract

Wind speed and power at wind power stations affect the efficiency of a wind farm, so accurate wind forecasting, a nonlinear signal with high fluctuations, increases security and better efficiency than wind power. We are looking for wind speed for a wind farm in Iran. In this research, a combined neural network created from variational autoencoder (VAE), long-term, short-term memory (LSTM), and multilayer perceptron (MLP) for dimension Reduction and encoding is proposed for predicting short-term wind speeds. The data used in this research is related to the statistics of 10 minutes of wind speed in 10- meter, 30-meter, and 40-meter wind turbines, the standard deviation of wind speed, air temperature, and humidity. To compare the proposed model (V- LSTM-MLP), we implemented three deep neural network models, including Stacked Auto-Encoder (SAE), recurrent neural networks (Regular LSTM), and hybrid model Encoder-Decoder recurrent network (LSTM-Encoder-MLP) presented on this dataset. According to the RMSE statistical index, the proposed model is worth 0.1127 for a short time and performs better than other types on this dataset.