One-Month Ahead Prediction of Wind Speed and Output Power Based on EMD and LSSVM

Abstract

Wind speed is a kind of non-stationary time series, it is difficult to construct the model for accurate forecast. The way improving accuracy of the model for predicting wind speed up to one-month ahead has been investigated using measured data recorded by wind farm. A forecasting method based on empirical mode decomposition (EMD) and least square support vector machine (LSSVM) is proposed in this paper. The non-stationary time series is decomposed into several intrinsic mode functions (IMF) and the trend term. The different LSSVM models to forecast each IMF are built up. These forecasting results of each IMF are combined to obtain the final forecasting result. Considering the power characteristics, unit efficiency and the operate condition of the generators, the one-month ahead forecasted output power of the wind power plant can be obtained.