Short-term wind speed forecasting using variational mode decomposition and support vector regression

Abstract

Wind speed forecasting is a prerequisite and a guarantee for the efficient operation of wind farms. Estimation of the non-stationary property and prediction of the future moving average of wind speed are challenging because of various environmental factors. In this paper, a new model is proposed for wind speed forecasting. The proposed model consists of three main stages: preprocessing, regression, and aggregation. In the first stage, the original wind speed time series is decomposed into different subseries by using the variational mode decomposition technique. These subseries are then used to construct training patterns and forecasted outputs. In the second stage, support vector regression is applied to fit and forecast the wind speed for each subseries. Eventually, the final forecasted wind speed is calculated by summing all the forecasting values of each subseries. The performance of the proposed model is evaluated using real data collected from a wind farm in China, and the experimental results confirm the superiority of the proposed model to the existing models with respect to accurate forecasting and stability.