基于AVMD-CNN-GRU-Attention的超短期风功率预测研究
RESEARCH ON ULTRA-SHORT-TERM WIND POWER FORECAST BASED ON AVMD-CNN-GRU-Attention
任东方 1马家庆 1何志琴 1吴钦木1
作者信息
- 1. 贵州大学电气工程学院,贵阳 550025
- 折叠
摘要
为提高超短期风功率的预测精度,提出一种改进的基于变分模态分解的卷积神经网络(AVMD-CNN)、门控循环单元(GRU)和注意力机制(Attention)的超短期风功率预测模型.首先利用改进的VMD将风功率序列分解为K个子模态;然后将各子模态利用样本熵(SE)和中心频率进行分类,根据分类结果对各子模态分别给定归一化方式,并按SE值分别输入到GRU-Attention和CNN-GRU-Attention模型中进行训练和预测;最后将各子模态预测结果叠加得到最终结果,从而完成超短期风功率预测.以决定系数(R2)、平均绝对误差(MAE)、均方根误差(RMSE)以及平均绝对百分比误差(MAPE)为精度评估指标,实际算例表明,所提出模型的R2较文中其他方法平均提高12.06%,MAE、RMSE以及MAPE分别平均降低59.36%、62.49%和48.34%,具有较高的预测精度.
Abstract
In order to improve the forecast accuracy of ultra-short-term wind power,an improved ultra-short-term wind power forecast model based on variational mode decomposition convolutional neural network(AVMD-CNN),gated recurrent unit(GRU)and attention mechanism(Attention)is proposed.Firstly,the wind power sequence is decomposed into K sub-modes by using the improved VMD.Then,each sub-mode is classified by sample entropy(SE)and center frequency.According to the classification results,each sub-mode is given a normalization method,and input into GRU-Attention and CNN-GRU-Attention models for training and forecasting according to SE values.Finally,the final results are obtained by superimposing the forecast results of each sub-mode,so as to complete the ultra-short-term wind power forecast.Using the determination coefficient(R2),mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)as the accuracy assessment indexes,the actual arithmetic examples show that the R2 of the proposed model is improved by 12.06% on average compared with other methods,and the MAE,RMSE,and MAPE are reduced by 59.36%,62.49%,and 48.34% respectively,with high prediction accuracy.
关键词
风功率/预测/变分模态分解/卷积神经网络/注意力机制/样本熵Key words
wind power/forecasting/variational mode decomposition/convolutional neural network/attention mechanism/sample entropy引用本文复制引用
基金项目
国家自然科学基金(51867006)
贵州省科技厅项目(黔科合支撑[2021]一般442)
贵州省科技厅项目([2022]一般264)
贵州省科技厅项目([2023]一般096)
贵州省科技厅项目([2023]一般179)
出版年
2024
NETL
NSTL
万方数据