Short-Term Wind Power Forecasting and Uncertainty Analysis Based on Hybrid Temporal Convolutional Network

Abstract

The integration of large-scale wind power into power grids has made accurate short-term wind power forecasting a key technology for the safe and economical operation of power grids. A novel method based on variational mode decomposition (VMD), temporal convolutional network (TCN), and Gaussian mixture model (GMM) was proposed for accurate short-term wind power forecasting and uncertainty analysis. First, the wind speed information was decomposed into different mode components via VMD. Second, TCN was employed to capture accurately the time-series dependence of data by training and forecasting different mode component data. On this basis, GMM was used to calculate the distribution characteristics of short-term wind power forecasting errors and quantify the confidence interval of wind power forecasting. Results demonstrated that the root mean square error (RMSE) value of the VMD-TCN model for wind power forecasting for 4 h during winter is 4.69%, 3.13%, 2.48%, 1.21%, and 0.7% lower than the RMSE values of wavelet neural network, BP neural network, PSO-BP hybrid model, long short-term memory model, and TCN model, respectively. The proposed method has a certain promoting effect on improving the accuracy of short-term wind power forecasting.