Novel Multi-Step Short-Term Wind Power Prediction Framework Based on Chaotic Time Series Analysis and Singular Spectrum Analysis

Decomposition methods are widely applied as a prestage of wind power prediction (WPP) to reduce the prediction errors caused by the nonstationarity and nonlinearity of wind power time series (TS); however, they cannot address the issues posed by the chaotic behavior of wind power TS. This paper, therefore, proposes a novel decomposition approach to take the chaotic nature of wind power TS into account and to improve WPP accuracy. In this decomposition approach, as a primary step, the wind power TS is separated into several components with different time-frequency characteristics (scales) by means of ensemble empirical mode decomposition. Chaotic TS analysis is then applied to determine which components are chaotic, and then singular spectrum analysis (SSA) is applied thereto. This multi-scale SSA (MSSSA) can maintain the general trend of chaotic components, which become smoother by eliminating extremely rapid changes with low amplitudes, and thus several steps ahead WPP with higher accuracy can be realized. Following the proposed decomposition, a novel short-term WPP method comprised of localized direct and iterative prediction is proposed to perform multi-step prediction for the chaotic and nonchaotic components of MSSSA, respectively. The proposed framework is finally validated using historical data related to overall wind power generation for Alberta (Canada), the Sotavento wind farm (Spain), and Centennial wind farm in Saskatchewan (Canada).