| 基于特征变权的超短期风电功率预测 |
| |
| 引用本文： | 王晓东,栗杉杉,刘颖明,敬彤辉,高兴.基于特征变权的超短期风电功率预测[J].太阳能学报,2023,44(2):52-58. |
| |
| 作者姓名： | 王晓东 栗杉杉 刘颖明 敬彤辉 高兴 |
| |
| 作者单位： | 沈阳工业大学电气工程学院,沈阳 110870 |
| |
| 基金项目： | 辽宁省中央引导地方科技发展资金计划（2021JH6/10500166）; 辽宁省“兴辽英才计划”（XLYC1802041） |
| |
| 摘 要： | 针对当前风电功率预测过程中历史信息利用不充分及多维输入权重值固定忽略了不同时间维度的特征重要性的问题，提出一种基于特征变权的风电功率预测模型。该方法利用随机森林（RF）分析不同高度处的风速、风向、温度等气象特征对风电输出功率的影响程度，并利用累积贡献率完成气象特征的提取。对提取的特征及历史功率信息利用奇异谱分析（SSA）去噪，以去噪后的数据作为输入建立级联式FA-CNN-LSTM多变量预测模型对超短期风电功率进行预测。通过在CNN-LSTM网络中增加特征注意力机制（FA）自适应挖掘不同时刻的特征关系，动态调整不同时间维度各输入特征的权重，加强预测时刻关键特征的注意力，从而提升预测性能。基于某风电场实测数据的算例分析表明，所提方法可有效提高超短期风电功率预测精度。
|
| 关 键 词： | 风电功率预测 长短期记忆 随机森林 奇异谱分析 注意力机制 |
| 收稿时间： | 2021-05-27 |
ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON VARIABLE FEATURE WEIGHT |
| |
| Wang Xiaodong,Li Shanshan,Liu Yingming,Jing Tonghui,Gao Xing.ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON VARIABLE FEATURE WEIGHT[J].Acta Energiae Solaris Sinica,2023,44(2):52-58. |
| |
| Authors: | Wang Xiaodong Li Shanshan Liu Yingming Jing Tonghui Gao Xing |
| |
| Affiliation: | School of Electrical Engineering, Shenyang University of Technology, Shenyang 110870, China |
| |
| Abstract: | Aiming at the problems of insufficient utilization of historical information and the fixed multi-dimensional input weight ignoring the importance of features in different time dimensions in current wind power prediction process, a wind power prediction model based on feature variable weight is proposed. Random forest （RF） is used to analyze the degree of influence of wind speed, wind direction, temperature and other meteorological characteristics at different heights on the wind power and cumulative contribution rate is used to complete the extraction of meteorological features. Singular spectrum analysis （SSA） is used to denoise the extracted features and historical power information, and the denoised data is used as input to establish a cascaded FA-CNN-LSTM multivariate prediction model to predict ultra-short-term wind power. By adding feature attention mechanism （FA） to CNN-LSTM network to adaptively mine feature relationships at different time, the weights of input features at different time dimensions can be dynamically adjusted to enhance the attention of key features at prediction moment, and the prediction performance can be improved. The case study shows that the proposed method can effectively improve the accuracy of ultra-short-term wind power prediction. |
| |
| Keywords: | wind power prediction long short-term memory random forest singular spectrum analysis attention mechanism |
|
| 点击此处可从《太阳能学报》浏览原始摘要信息 |
|
点击此处可从《太阳能学报》下载全文 |
|
