###
DOI:
电力大数据:2024,27(6):-
←前一篇   |   后一篇→
本文二维码信息
基于VMD-CNN-LSTM-CBAM的配变短期负荷预测方法
何晔1, 殷若宸2, 陆之洋3, 徐小东1, 徐玉韬4
(1.贵州电网有限责任公司安顺供电局;2.贵州大学;3.电气工程学院;4.贵州电网有限责任公司电力科学研究院)
A method of distribution transformer overload warning based on VMD-CNN-LSTM-CBAM
(He Ye1, Yin Ruochen2, Lu Zhiyang3, Xu Xiaodong1, Xu Yutao4
(1.Anshun Power Supply Bureau of Guizhou Power Grid Co., Ltd.;2.Guizhou university;3.贵州大学;4.Electric Power Science Research Institute of Guizhou Power Grid Co., Ltd.,)
摘要
图/表
参考文献
相似文献
本文已被:浏览 36次   下载 24
投稿时间:2024-06-26    修订日期:2024-08-28
中文摘要: 为提高配变重过载预警的准确性,本文提出了一种基于VMD-CNN-BiLSTM-CBAM模型的配变短期负荷预测方法。该方法首先利用K均值聚类提取相似日,采取变分模态分解(VMD)对相似日负荷进行分解得到IMF分量,对各IMF分量采用卷积神经网络(CNN)-双向长短时记忆网络(BiLSTM)-双重自注意力机制(CBAM)相结合的模型进行预测,最后,利用样本熵将各预测分量进行重构获得配变预测日负荷曲线。算例表明,本文所提方法相较卷积神经网络CNN、自适应模糊神经网络模型ANFIS等方法,预测精度高,可为后续配变重过载预警提供技术支撑。
Abstract:In order to improve the accuracy of distribution substation heavy overload warning, this paper proposes a short-term load prediction method for distribution substation based on VMD-CNN-BiLSTM-CBAM model. The method firstly extracts similar days using K-mean clustering, adopts variational modal decomposition (VMD) to decompose the load on similar days to obtain IMF components, and adopts the model combining convolutional neural network (CNN)-bi-directional long and short-term memory network (BiLSTM)-double self-attention mechanism (CBAM) for each IMF component to make a prediction, and finally, utilizes the sample entropy to reconstruct the predicted daily load curves of distribution substation to obtain the predicted daily load curves of distribution substation. Finally, the sample entropy is used to reconstruct each prediction component to obtain the daily load curve of distribution variable prediction. Examples show that the method proposed in this paper has high prediction accuracy compared with the methods of convolutional neural network (CNN) and adaptive fuzzy neural network model (ANFIS), which can provide technical support for the subsequent heavy overload warning of distribution substation.
文章编号:     中图分类号:    文献标志码:
基金项目:国家重点研发计划项目(2022YFE0205300),国家自然科学基金(52367005)
引用文本: