基于DTW-FCBF-LSTM模型的超短期风速预测

董治强

董治强.基于DTW-FCBF-LSTM模型的超短期风速预测[J].电测与仪表,2020,57(4):93-98.
dongzhiqiang.Ultra-Short Term Wind Speed Prediction Based on DTW-FCBF-LSTM Model[J].Electrical Measurement & Instrumentation,2020,57(4):93-98.

基于DTW-FCBF-LSTM模型的超短期风速预测

Ultra-Short Term Wind Speed Prediction Based on DTW-FCBF-LSTM Model

DOI：10.19753/j.issn1001-1390.2020.04.015

中文关键词: 风速预测人工智能动态时间规整快速相关过滤式算法长短期记忆神经网络

英文关键词:wind speed prediction artificial intelligence dynamic time warping fast correlation-based filter algorithm long-short term memory network

基金项目:

作者中文名	作者英文名	单位
董治强	dongzhiqiang	河海大学能源与电气学院

摘要点击次数: 2112

中文摘要:

为了实时调整电网调度计划、提高电网消纳风电的能力,提出了一种基于动态时间规整(DTW)进行相似数据分析、快速相关过滤方法(FCBF)进行输入属性特征选择、以及基于长短期记忆神经网络(LSTM)的超短期风速预测方法。首先利用DTW方法筛选出与预测数据相似性高的训练样本；然后运用FCBF算法得到优选的输入特征集；最后,构建LSTM模型进行超短期风速预测。以风电场实测数据为算例,将文中方法与现有算法的预测精度进行了对比,验证了所提方法的有效性和先进性。

英文摘要:

In order to adjust the grid dispatching plan in real time and improve the grid"s ability to absorb wind power , a new ultra-short term wind speed prediction method is put forward based on dynamic time warping (DTW)-fast correlation-based filter(FCBF) and long-short term memory neural network(LSTM). Firstly, similarity of historical wind speed data is analyzed by using DTW method, and high similarity data to the predicted day are selected. Secondly, the FCBF method is used to select the optimal input feature set. Finally, the LSTM model is applied to predict the ultra-short term wind speed. The measured data of wind farm are forecasted, and the effectiveness and superiority of the proposed method is verified by comparing the prediction error with existing methods.

查看全文查看/发表评论下载PDF阅读器

关闭