Short-term wind power forecast based on chaotic analysis and multivariate phase space reconstruction
Tianyao Ji, Jin Wang, Mengshi Li, Qinghua Wu
Abstract
The randomness and volatility of wind power time series, which are an external reflection of their internal chaotic dynamics, have always been important factors affecting the accuracy of wind power prediction. The chaotic characteristics of wind power data have not been studied deeply enough in existing research. Therefore, in this paper, a short-term wind power forecast method based on chaotic analysis is proposed, including chaotic time series estimation and multivariate phase space reconstruction (PSR). First, we calculate the largest Lyapunov exponent of wind power time series to measure the degree of chaos in wind power data. Then, the chaotic characteristics of several wind power time series from some neighboring wind farms are analyzed, based on which two multivariate multi-dimensional PSR models are established. Afterwards, the nearest neighbors (NNs) of the data to be predicted are selected in the phase space and delivered to the least-square support vector machine (LSSVM) model to experiment the forecasting. Wind power data collected from several adjacent wind sites are used to conduct the simulation studies, and the results have shown the effectiveness of the proposed method and its advantage over the classic LSSVM model in terms of accuracy and stability.