| 基于多层语义融合注意力机制的短期风电功率概率密度预测方法 |
| |
| 引用本文： | 綦方中,卓可翔,曹柬.基于多层语义融合注意力机制的短期风电功率概率密度预测方法[J].太阳能学报,2022,43(11):140-147. |
| |
| 作者姓名： | 綦方中 卓可翔 曹柬 |
| |
| 作者单位： | 浙江工业大学管理学院,杭州 310023 |
| |
| 基金项目： | 国家自然科学基金（71874159） |
| |
| 摘 要： | 获得未来风电功率的短期概率性信息将有助于电网的综合能源调度,为此提出一种结合多层语义融合注意力机制的短期风电功率概率密度预测方法。为尽可能获得更多语义层下的编码信息,在编码阶段引入循环高速网络（RHN）并通过深层的RHN网络结构最大程度地提取输入特征的底层关联信息。设计多层语义融合注意力机制以融合不同语义层下的局部注意力向量,进一步加强编码特征向量的表达能力,并将网络的输出与分位数回归和核密度估计方法结合,得到不同分位点下未来短期风电功率的预测结果与连续概率密度分布。实验结果表明：提出的短期风电功率概率密度预测方法不论是在预测的得精度上,还是在具有不确定性的预测结果分布上均优于其他比较模型。
|
| 关 键 词： | 风电功率 深度学习 概率密度 分位数回归 循环高速网络 |
| 收稿时间： | 2022-01-31 |
SHORT-TERM WIND POWER PROBABILITY DENSITY PREDICTION METHOD BASED ON MULTI-LEVEL SEMANTIC ATTENTION MECHANISM |
| |
| Qi Fangzhong,Zhuo Kexiang,Cao Jian.SHORT-TERM WIND POWER PROBABILITY DENSITY PREDICTION METHOD BASED ON MULTI-LEVEL SEMANTIC ATTENTION MECHANISM[J].Acta Energiae Solaris Sinica,2022,43(11):140-147. |
| |
| Authors: | Qi Fangzhong Zhuo Kexiang Cao Jian |
| |
| Affiliation: | School of Management, Zhejiang University of Technology, Hangzhou 310023, China |
| |
| Abstract: | Obtaining short-term probabilistic information of future wind power will improve the comprehensive energy dispatching of power grid. Therefore, a method of short-term wind power probability density prediction based on multi-level semantic attention mechanism is proposed. In order to obtain as much coding information as possible at the semantic level, Recurrent Highway Network （RHN） is introduced at the encoding stage. The underlying association information of input features is extracted to the maximum extent through the deep RHN network structure. A multi-level semantic attention mechanism is designed to integrate local attention vector under different semantic layers, which further strengthen the expression ability of coding feature vector. Combining the output of network with quantile regression and kernel density estimation methods, the prediction results and continuous probability density distribution of future short-term wind power are obtained. The experimental results show that the proposed method of short-term wind probability density prediction is superior to other comparison models, in terms of the accuracy of prediction value and the distribution of prediction results with uncertainty. |
| |
| Keywords: | wind power deep learning probability density quantile regression recurrent highway network |
|
| 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 |
|
