基于经验模式分解的风电场短期风速预测模型

Short-term wind speed forecasting for wind farms based on empirical mode decomposition model

采用经验模式分解(EMD)和时间序列相结合的方法进行风电场的短期风速预测。针对风速序列的非平稳性和时序性,利用EMD分析非线性、非平稳信号的特点和自回归滑动平均(ARMA)时间序列的建模方法,建立风电场短期风速预测的EMD-ARMA模型。该模型通过EMD方法将原始风速序列进行分解,运用ARMA时间序列的方法对各分量分别进行预测。通过对我国某风电场的实际风速序列进行分析预测,介绍方法的实现过程,证明该方法的有效性。

Accurate wind speed forecasting of a wind farm is necessary for the dispatching of the power system. It can relieve the disadvantageous impact to the electric network. A new technique was presented for wind speed forecasting based on empirical mode decomposition （EMD） and ARMA. EMD is a new method for analyzing nonlinear and non-stationary signal. It can decompose non-stationary signals into some smooth and stationary intrinsic mode function （IMF） with different frequency in the different scale space by the sifting process. The characteristic of the EMD and the ARMA in the EMD-ARMA model was fully used. Actual wind speed data were used to test the approach. The results indicate that EMD-ARMA model is an effective method in wind speed forecasting.