[1]蒋建东,赵云飞,韩文轩,等.基于组合深度学习的风电功率区间预测[J].郑州大学学报(工学版),2025,46(03):50-58.[doi:10.13705/j.issn.1671-6833.2025.03.020]
　JIANG Jiandong,ZHAO Yunfei,HAN Wenxuan,et al.Wind Power Interval Prediction Based on Combined Deep Learning[J].Journal of Zhengzhou University (Engineering Science),2025,46(03):50-58.[doi:10.13705/j.issn.1671-6833.2025.03.020]

点击复制

基于组合深度学习的风电功率区间预测()

分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:

46

期数:

2025年03期

页码:

50-58

栏目:

出版日期:

2025-05-13

文章信息/Info

Title:

Wind Power Interval Prediction Based on Combined Deep Learning

文章编号:

1671-6833(2025)03-0050-09

作者:

蒋建东¹;  赵云飞¹;  韩文轩¹;  燕跃豪²;  鲍　薇²;  刘晓辉²

1.郑州大学 电气与信息工程学院,河南 郑州 450001;2.国网河南省电力公司郑州供电公司,河南 郑州 450006

Author(s):

JIANG Jiandong¹;  ZHAO Yunfei¹;  HAN Wenxuan¹;  YAN Yuehao²;  BAO Wei²;  LIU Xiaohui²

1.School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China; 2.Zhengzhou Power Supply Company,State Grid Henan Electric Power Company, Zhengzhou 450006,China

关键词:

风电功率区间预测;  蜣螂优化算法;  变分模态分解;  非参数核密度估计

Keywords:

wind power interval prediction;  dung beetle optimization algorithm;  variational mode decomposition;  kernel density estimation

分类号:

TM614

DOI:

10.13705/j.issn.1671-6833.2025.03.020

文献标志码:

A

摘要:

为了提高风电功率区间预测的精度,提出了一种基于组合深度学习的风电功率区间预测模型。首先,针对传统蜣螂优化算法(DBO)存在全局寻优能力和局部探索能力不均衡的问题,提出了一种改进的蜣螂优化算法(POTDBO)。该算法通过增强全局寻优能力并改进局部探索策略,优化变分模态分解(VMD)中的分解个数K和惩罚因子β,从而提高VMD的分解效果。其次,基于优化后的VMD分解结果,构建了组合深度学习模型POTDBOVMD-CNN-BiLSTM。该模型利用卷积神经网络(CNN)提取风电功率的空间特征,并结合双向长短期记忆网络(BiLSTM)充分捕捉数据中的历史信号特征和未来信号特征,对各分量分别预测并叠加重构,从而实现了风电功率的准确预测。再次,引入了非参数核密度估计法(KDE)对组合模型的预测误差进行拟合,从而得到不同置信区间下的风电功率区间预测结果。最后,运用新疆某风电场的实际运行数据对所提模型进行了验证。仿真结果表明:在置信水平为95%时,与高斯分布、T分布相比,所提方法在预测区间覆盖宽度CWC上分别降低了0.103 6, 0.171 4,在区间预测精度上有所提升。

Abstract:

To improve the accuracy of wind power interval prediction, in this study, a combined deep learningbased wind power interval prediction model was proposed. Firstly, to address the imbalance between global optimization ability and local exploration in the traditional dung beetle optimization (DBO) algorithm, an improved version POTDBO was introduced. This algorithm enhanced the global search capability and improved the local search strategy. By optimizing the decomposition number K and penalty factor β in the variational mode decomposition (VMD), thus it improved the decomposition performance of VMD. Secondly, based on the optimized VMD decomposition results, a combined deep learning model, POTDBO-VMD-CNN-BiLSTM, was established. In this model, convolutional neural networks (CNN) were used to extract the spatial features of wind power, and a bidirectional long short-term memory (BiLSTM) network was applied to capture both historical and future signal features in the data. The individual components were predicted and then combined to reconstruct the wind power prediction accurately. To perform interval prediction for wind power, in this study the non-parametric kernel density estimation (KDE) method was introduced to fit the prediction errors of the combined model, then to obtain wind power interval prediction results at different confidence levels. Finally, the proposed model was validated using actual operation data from a wind farm in Xinjiang. Simulation results showed that, at a 95% confidence level, compared to the Gaussian and T-distribution models, the proposed method reduced the prediction interval coverage width (CWC) by 0.103 6 and 0.171 4, respectively, while improving the interval prediction accuracy.

常用功能