基于EMD-PCA-LSTM的短期风电功率预测研究

Short-term wind power prediction based on EMD-PCA-LSTM

精准的风电功率预测有利于全网电力平衡、系统安全稳定运行和节能减耗,提出一种基于EMD-PCA-LSTM的短期风电功率预测模型。先采用经验模态分解技术将多维气象序列分解为多个固有模态分量,以挖掘原始数据的主要特征并消除噪声。再引入主成分分析进行降维处理,提取数据的非线性特征,最后使用长短期记忆神经网络进行预测。通过与多种预测模型进行比较,证明了该模型在预测精度方面的卓越表现。

Accurate wind power prediction is conducive to power balance of the whole grid,safe and stable operation of the system,energy saving and consumption reduction,therefore a short-term wind power prediction model based on EMD-PCA-LSTM is proposed.Firstly,the empirical mode decomposition(EMD)method is used to decompose the multi-dimensional meteorological series into multiple inherent modal components to mine the main features of the original data and eliminate noise.Then principal component is analyzed to reduce the dimension and extract nonlinear features of data,,and long short-term memory neural network is used for prediction.The excellent performance of this model in forecasting accuracy is proved by comparing with many forecasting models.