A hybrid model of EMD and multiple-kernel RVR algorithm for wind speed prediction

• EMD-MkRVR is proposed for wind speed forecasting.
• Wind speed is decomposed into six IMFs with different frequency range.
• Establish each IMF’s MkRVR model with respective appropriate embedding dimension.

In this paper, the hybrid model of empirical mode decomposition and multiple-kernel relevance vector regression algorithm (EMD-MkRVR) is presented for wind speed prediction. The multiple-kernel relevance vector regression (MkRVR) model includes radial basis function (RBF) kernel and polynomial kernel whose proportions are determined by a controlled parameter. Grid method is used to select the kernel parameters and controlled parameter in this study. In addition, wind speed can be regarded as a signal and decomposed into several intrinsic mode functions (IMFs) with different frequency range by empirical mode decomposition (EMD), the prediction models of these decomposed signals can be established by MkRVR with their respective appropriate embedding dimension. The experimental results show that the EMD-MkRVR model has a better prediction ability for wind speed than the RBF kernel RVR (RBFRVR) model and the polynomial kernel RVR (PolyRVR) model.