基于ARIMA与ESN的短期风速混合预测模型  

SHORT-TERM WIND SPEED HYBRID PREDICTION MODEL BASED ON ARIMA AND ESN

作　　者：田中大[1] 李树江[1] 王艳红[1] 高宪文[2] 

机构地区：[1]沈阳工业大学信息科学与工程学院,沈阳110870 [2]东北大学信息科学与工程学院,沈阳110819

出　　处：《太阳能学报》2016年第6期1603-1610,共8页Acta Energiae Solaris Sinica

基　　金：国家自然科学基金(61034005)

摘　　要：提出一种基于自回归求和滑动平均模型(autoregressive integrated moving average,ARIMA)与回声状态网络(echo state network,ESN)的短期风速预测模型。首先利用ARIMA模型对短期风速时间序列进行线性特征的预测,使得短期风速的残差仅包含非线性特征,然后利用ESN模型对非线性的残差序列进行预测,最后将ARIMA模型的短期风速线性预测值与ESN模型的短期风速非线性预测残差值进行相加得到最终的短期风速的预测值。单步与多步预测的仿真实验表明该混合预测模型具有更高的预测精度与更小的预测误差。A short-term wind speed hybrid prediction model was proposed based on autoregressive integrated moving average （ARIMA） and echo state network （ESN）. Firstly, ARIMA model was used to predict the linear characteristics of short-term wind speed time series, and make the residual error of short-term wind speed only include the nonlinear characteristics. Then ESN model was used to predict the nonlinear residual error series of wind speed. Finally, the ultima prediction value of short-term wind speed could be obtained by adding short-term linear prediction value of ARIMA model with short-term nonlinear prediction residual error value of ESN model. The simulation experiments of single-step and multi-step prediction show that the hybrid prediction model has higher prediction precision and smaller prediction error.

关 键 词：短期风速 预测 自回归求和滑动平均模型 回声状态网络 

分 类 号：TM614[电气工程—电力系统及自动化]