Short-term wind power prediction using differential EMD and relevance vector machine

Abstract

As a renewable energy source, wind turbine generators are considered to be important generation alternatives in electric power systems because of their nonexhaustible nature. With the increase in wind power penetration, wind power forecasting is crucially important for integrating wind power in a conventional power grid. In this paper, a short-term wind power output prediction model is presented from raw data of wind farm, and prediction of short-term wind power is implemented using differential empirical mode decomposition (EMD) and relevance vector machine (RVM). The differential EMD method is used to decompose the wind farm power to several detail parts associated with high frequencies [intrinsic mode function (IMF)] and an approximate part associated with low frequencies (r). Then, RVM is used to predict both the IMF components and the r. Finally, the short-term wind farm power is forecasted by summing the RVM-based prediction of both the IMF components and the r. Simulation results have shown that the proposed short-term wind power prediction method has good performance.