Short-term prediction of wind power based on temporal convolutional network and the informer model

In this study, a new short-term wind power prediction model based on a temporal convolutional network (TCN) and the Informer model is proposed to solve the problem of low prediction accuracy caused by large wind speed fluctuations in short-term prediction. First, an input feature selection method based on the maximum information coefficient is proposed after considering the problem of information interference caused by excessively large input features. A dynamic time planning method is used to select the optimal input step of historical power. Then, the combined forecasting model composed of TCN and the Informer is constructed in accordance with the numerical weather forecast and historical power data. Lastly, the pinball loss function is used to expand the prediction model into a quantile regression model, measure the effect of volatility, quantify the volatility range of prediction, and finally, obtain a deterministic prediction result. The actual measured data of wind farms in the Bohai Sea area are selected for analysis and calculation. The results show that the prediction model proposed in this study achieves better accuracy in deterministic prediction and interval prediction than the traditional model. To solve the problem of information interference caused by excessively large input features in practical applications, an input feature selection method based on MIC is proposed. A two-stage prediction model is proposed to address the low efficiency of the short-term prediction of wind power. To measure the effect of volatility on the basis of deterministic prediction, the quantile regression model of temporal convolutional network-Informer is obtained by using the pinball loss function. The volatility range of deterministic prediction is quantified.image