An ultra-short-term wind speed prediction model using LSTM and CNN

Gale weather can easily cause high-speed train accidents such as derailment and rollover. Therefore, the ultra-short-term prediction of wind speed is of great significance for a safe operation of high-speed rail. A prediction model based on long short-term memory (LSTM) networks and convolutional neural network (CNN) is proposed in this paper. The maximum wind speed data per minute collected by WindLog wind speed sensor is pre-processed. Setting includes reasonable step parameters and convolution kernel to establish a prediction model combined with two-layer LSTM and two-layer CNN. The proposed model was tested using wind speed data of Haidian District, and the wind speeds of 1 min, 5 min and 10 min ahead were predicted. The mean absolute error (MAE) of 1 min ahead prediction was 0.487 m/s. The MAE of 5 min ahead prediction is 0.547 m/s. The MAE of 10 min ahead prediction is 0.593 m/s. The predicting performances of different models are compared by using the same data. The experimental results show that the proposed prediction model has better adaptability and higher prediction accuracy.