Multi-time scale wind speed prediction method and system based on hybrid prediction model

• Main Authors: TIAN CHONGYI, SHAO ZHULIANG, REN FEI, YAN YI, WANG XUERUI, TIAN CHENLU, WANG RUIQI
• Format: Patent
• Language: Chinese; English
• Published: 03.01.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a multi-time scale wind speed prediction method and system based on a hybrid prediction model, and relates to the technical field of power systems. Using an integrated moving average autoregression model to extract linear features of wind speed time sequences of all time scales, using an ensemble empirical mode decomposition model to decompose a nonlinear residual sequence, and using a long and short-term memory neural network model to predict decomposed subsequences; and integrating the predicted subsequences, and adding the integrated subsequences with the extracted linear time sequence to obtain a final predicted wind speed time sequence. According to the method, the non-stationary characteristic of the wind speed is considered, and high-efficiency and high-accuracy prediction of the wind speed is realized through multiple models based on multiple time scales. 本发明公开了一种基于混合预测模型的多时间尺度风速预测方法及系统，涉及电力系统技术领域。使用整合移动平均自回归模型提取各时间尺度风速时间序列的线性特征、使用集合经验模态分解模型将非线性残差序列分解、使用长短期记忆神经网络模型对分解的子序列进行预测、将