| 引用本文: | 马艺玮,刘智强,邹 密,等.基于多维数据融合和CNN-BiLSTM联合优化的超短期风电功率预测[J].电力系统保护与控制,2026,54(05):24-33. |
| MA Yiwei,LIU Zhiqiang,ZOU Mi,et al.Ultra-short-term wind power forecasting based on multidimensional data fusion and joint optimization of CNN-BiLSTM[J].Power System Protection and Control,2026,54(05):24-33 |
|
| 摘要: |
| 风电功率的精准预测是提升风电并网稳定性和风电场经济收入的一项有效解决方案。针对自然气象特征的复杂性与随机性导致风电功率难以精准预测的突出问题，提出了一种综合考虑多维数据融合和卷积双向长短期记忆神经网络(convolutional neural network-bidirectional long short-term memory network, CNN-BiLSTM)联合优化的超短期风电功率预测方法。该方法主要包括两个阶段。首先，在输入数据处理阶段，通过将主成分分析(principal component analysis, PCA)选择的关键气象因素与最优变分模态分解(optimal variational mode decomposition, OVMD)得到的风电功率固有模态分量相结合，构建一种新的多维特征数据以提高预测模型的准确性。其次，在预测模型的联合优化阶段，先构建了一个集成卷积神经网络(convolutional neural network, CNN)和BiLSTM的串联式结构预测组合模型，再通过使用红嘴蓝喜鹊优化算法(red-billed blue magpie optimizer, RBMO)对CNN和BiLSTM模型进行联合优化，从而充分发挥二者之间互补优势来提高预测精度。通过对风电功率预测的比较分析，结果充分证明所提出的PCA-OVMD-RBMO-(CNN-BiLSTM)预测方法比其他对比预测方法具有更高的预测精度。 |
| 关键词: 风电功率预测 主成分分析 最优变分模态分解 卷积神经网络 双向长短期神经网络 |
| DOI：10.19783/j.cnki.pspc.250635 |
| 分类号: |
| 基金项目:国家自然科学基金项目资助(61703068)；重庆市教育委员会科学技术研究项目资助(KJQN202504202)；重庆市研究生科研创新项目资助(CYS23468，CYS23469) |
|
| Ultra-short-term wind power forecasting based on multidimensional data fusion and joint optimization of CNN-BiLSTM |
|
MA Yiwei, LIU Zhiqiang, ZOU Mi, CHEN Junsheng, YAN Dong
|
|
School of Automation/School of Industrial Internet, Chongqing University of Posts and
Telecommunications, Chongqing 400065, China
|
| Abstract: |
| Accurate wind power forecasting is an effective means of improving the stability of wind power grid integration and the economic performance of wind farms. Aiming at the prominent challenge that the complexity and randomness of natural meteorological characteristics make wind power difficult to predict accurately, this paper proposes an ultra-short-term wind power forecasting method based on multidimensional data fusion and the joint optimization of a convolutional neural network-bidirectional long short-term memory network (CNN-BiLSTM). The method consists of two main phases. First, in the input data processing phase, a new multidimensional feature data is constructed to improve the accuracy of the prediction model, which combines the key meteorological factors selected by principal component analysis (PCA) with the wind power intrinsic modal components obtained via optimized variational mode decomposition (OVMD). Second, in the joint optimization phase of the forecasting model, a cascaded hybrid forecasting model integrating CNN and BiLSTM is constructed, and the red-billed blue magpie optimizer (RBMO) is employed to jointly optimize the CNN and BiLSTM models. This allows the complementary advantages of the two models to be fully exploited, further enhancing forecasting accuracy. Comparative analyses of wind power forecasting results demonstrate that the proposed PCA-OVMD-RBMO-(CNN-BiLSTM) method achieves higher prediction accuracy than other benchmark forecasting methods. |
| Key words: wind power forecasting principal component analysis optimal variational mode decomposition convolutional neural network bidirectional long short-term memory network |
