Agricultural load forecasting model based on multivariate temporal decoupling and multimodal learning

勇 晔; 薛溟枫; 毛晓波

doi:10.3969/j.issn.1009-1831.2025.05.004

您当前的位置：

首页 >

文章列表页 >

Agricultural load forecasting model based on multivariate temporal decoupling and multimodal learning

更新时间：2026-03-05

- Agricultural load forecasting model based on multivariate temporal decoupling and multimodal learning
- Vol. 27, Issue 5, (2025)
- 作者机构：
  
  国网江苏省电力有限公司无锡供电分公司,江苏,无锡,214125
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2025.05.004
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
勇晔, 薛溟枫, 毛晓波. Agricultural load forecasting model based on multivariate temporal decoupling and multimodal learning[J]. 2025, 27(5).
DOI：

勇晔, 薛溟枫, 毛晓波. Agricultural load forecasting model based on multivariate temporal decoupling and multimodal learning[J]. 2025, 27(5). DOI： 10.3969/j.issn.1009-1831.2025.05.004.

摘要

针对农业负荷受气象因素影响大，单一分解方法无法充分提取多元输入间存在的多维特征的问题，提出了一种基于多元变分模态分解结合SVR-Bi-GRU-TCN组合模型的农业负荷预测模型。首先利用多元变分模态分解对历史农业负荷及气象特征进行自适应分解，实时挖掘数据间不同特征尺度的模态分量，然后针对各模态分量的固有属性，分别建立SVR、Bi-GRU、TCN模型以提取不同时间尺度的特征信息，进而实现对未来1 h农业负荷精准预测。实验结果表明，与SVR模型、Bi-GRU模型、TCN模型、LSTM模型及CNN-Bi-LSTM模型相比，所提出的预测模型能有效提升预测精度。

Abstract

As the agricultural load is greatly affected by meteorological factors and a single decomposition method cannot fully extract the multidimensional features existing between multiple inputs

an agricultural load forecasting model based on multivariate variational mode decomposition combined with SVR Bi GRU TCN combined model is proposed. Firstly

using multivariate variational mode decomposition to adaptively decompose historical agricultural loads and meteorological characteristics

real-time mining of modal components with different feature scales between data is carried out. Then

based on the inherent properties of each modal component

SVR

Bi-GRU

and TCN models are established to extract feature information at different time scales

thereby achieving accurate prediction of future 1-hour agricultural loads. The experimental results show that compared with the SVR model

Bi-GRU model

and TCN model

LSTM model and CNN-BiLSTM model

the proposed prediction model can effectively improve the prediction accuracy.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Short-term power load forecasting method for industry based on multi scale weight adaptation and bidirectional gated recurrent unit

Short-term wind speed prediction model based on wavelet transform and bidirectional neural networks

Identification and correction method of bad data of new energy plants based on deep learning

Application of deep learning in power load analysis

Real⁃time energy management optimization strategy of electric vehicle based on LSTM network learning

Related Author

汤子琪

李卫

江山

刘佳林

付震宇

郭炜

王榆楗

王寅

Related Institution

阳光电源（上海）有限公司

贵州电网有限责任公司电力调度控制中心

电子科技大学机械与电气工程学院

北京东润环能科技股份有限公司

南京工程学院电力工程学院

AI问答

⁰