| 引用本文: | 杨信强,李振华,钟 悦,等.基于变分模态分解和CNN-GRU-ED的超短期互感器误差预测[J].电力系统保护与控制,2023,51(12):68-77. |
| YANG Xinqiang,LI Zhenhua,ZHONG Yue,et al.Ultra-short term transformer error forecast based on variational mode decomposition and CNN-GRU-ED[J].Power System Protection and Control,2023,51(12):68-77 |
|
| 摘要: |
| 准确的误差预测对及时发现互感器运行中的稳定性问题和保证电能贸易的公平性具有重要的意义。提出了一种基于变分模态分解(variational mode decomposition, VMD)和卷积神经网络-门控循环单元编解码模型(convolutional neural network-gated recurrent unit encoder to decoder moder, CNN-GRU-ED)的互感器误差超短期预测方法。首先，针对特征数目增多所带来的数据分析问题，利用传递熵(transfer entropy, TE)对原始特征进行降维，得到高相关性特征集。其次，将波动性较强的原始误差序列分解成为高、低频模态分量，同时引入粒子群优化算法(particle swarm optimization, PSO)确定VMD的关键参数。最后，对各分量分别建立相应的CNN-GRU-ED预测模型，将预测结果叠加得到最终预测值。以某变电站运行数据进行实验，结果表明所提出的方法在单步和多步预测问题上，相较于其他模型具有更好的预测效果。 |
| 关键词: 超短期预测 变分模态分解 编解码模型 多步预测 |
| DOI：10.19783/j.cnki.pspc.221507 |
| 分类号: |
| 基金项目:国家自然科学基金项目资助(52277012)；强电磁工程与新技术国家重点实验室开放课题资助(2022KF005) |
|
| Ultra-short term transformer error forecast based on variational mode decomposition and CNN-GRU-ED |
|
YANG Xinqiang1, 2, LI Zhenhua1, 2, ZHONG Yue1, 2, LI Hongbin3
|
|
1. Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station (China Three Gorges University),
Yichang 443002, China; 2. College of Electrical Engineering & New Energy, China Three Gorges University,
Yichang 443002, China; 3. State Key Laboratory of Strong Electromagnetic Engineering and New Technology,
Huazhong University of Science and Technology, Wuhan 430074, China
|
| Abstract: |
| Accurate prediction of error is significant for detecting a stability problem in a transformer in good time and ensuring the validity of electric power trade. An ultra-short-term transformer error prediction method based on variational mode decomposition (VMD) and an encoder-decoder model based on a convolutional neural network-gated recurrent unit encoder to decoder moder (CNN-GRU-ED) is proposed. First, because of the data analysis problem caused by the increase in the number of features, transfer entropy (TE) is used to reduce the dimensionality of the original features to obtain a highly correlated feature set. Second, the original error sequence with high fluctuation is decomposed into high and low-frequency modal components, in which the critical parameter of VMD is optimized by particle swarm optimization (PSO). Finally, the CNN-GRU-ED model is built for each component, and the predicted results are superimposed to obtain the final predicted value. Experiments with the operating data of a substation show that the performance of the proposed method is better than other models in single-step and multi-step prediction. |
| Key words: ultra-short-term prediction variational mode decomposition encoder-decoder multi-step prediction |
