基于ICPO优化VMD耦合深度学习模型的中短期风电功率预测

黄伟; 刘彬; 李火坤; 黄俊; 黄梓阳

doi:doi:10.19912/j.0254-0096.tynxb.2024-1820

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于ICPO优化VMD耦合深度学习模型的中短期风电功率预测

更新时间：2026-03-06

- 基于ICPO优化VMD耦合深度学习模型的中短期风电功率预测
- Vol. 47, Issue 2, Pages: 546-557(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1820
  CLC： TK8
- Online First：05 March 2026，
  
  Published：05 March 2026
- 稿件说明：
移动端阅览
黄伟, 刘彬, 李火坤, et al. 基于ICPO优化VMD耦合深度学习模型的中短期风电功率预测[J]. 2026, 47(2): 546-557.
DOI：

黄伟, 刘彬, 李火坤, et al. 基于ICPO优化VMD耦合深度学习模型的中短期风电功率预测[J]. 2026, 47(2): 546-557. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1820.

摘要

为提高风电功率的预测精度

增强混合模型的泛化性能

提出一种基于变分模态分解（VMD）耦合双向时域卷积网络（BiTCN）、双向长短期记忆网络（BiLSTM）和注意力机制（Attention）的混合中短期风电预测模型

并利用改进的冠豪猪算法（ICPO）优化VMD分解参数以及混合模型参数。该方法首先利用ICPO对VMD核心参数（K值和惩罚系数α）寻优

将原有的风电功率序列进行VMD分解;再引入ICPO对BiTCN-BiLSTM-Attention深度学习模型的超参数进行自动寻优

针对分解后的各分量分别建立ICPO-BiTCN-BiLSTM-Attention预测模型;最后叠加各分量的预测值得到最终预测值。某风电场实例验证表明

相比于单一预测模型和常规组合模型

提出的耦合模型在功率预测精度与泛化性能上均实现了显著提升。

Abstract

To improve the forecast accuracy of wind power and the generalization performance of the hybrid model

this paper proposes a hybrid medium-short-term wind power forecast model based on variational mode decomposition （VMD） coupled with bidirectional time convolutional network （BiTCN）

bidirectional long short-term memory network （BiLSTM）

and Attention mechanism. Furthermore

the model uses the improved crested porcupine optimizer （ICPO） to optimize the VMD decomposition parameters and the parameters of the hybrid model. Firstly

the ICPO is used to optimize the core VMD parameters （ value and penalty coefficient ）

and the original wind power sequence is decomposed by VMD. Then

the ICPO is introduced to automatically optimize the hyperparameters of the BiTCN-BiLSTM-Attention deep learning model

and the ICPO-BiTCN-BiLSTM-Attention forecast model is established for each component after decomposition. Finally

the prediction values of each component are superimposed to obtain the final prediction value. The verification of a certain wind farm instance indicates that compared with the single forecast models and the conventional combination models

the coupling model proposed in this paper achieves remarkable enhancements in both prediction accuracy and generalization performance.

关键词

Keywords

references

LIU K Y, CHEN W, CHEN G X, et al.Application and analysis of hydraulic wind power generation technology[J]. Energy strategy reviews, 2023, 48: 101117.

钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060.

冯双磊, 王伟胜, 刘纯, 等. 风电场功率预测物理方法研究[J]. 中国电机工程学报, 2010, 30(2): 1-6.

WANG S X, SHI J R, YANG W, et al.High and low frequency wind power prediction based on Transformer and BiGRU-Attention[J]. Energy, 2024, 288: 129753.

HE Y, WANG W, LI M, et al.A short-term wind power prediction approach based on an improved dung beetle optimizer algorithm, variational modal decomposition, and deep learning[J]. Computers and electrical engineering, 2024, 116: 109182.

刘建华, 李锦程, 杨龙月, 等. 基于EMD-SLSTM的家庭短期负荷预测[J]. 电力系统保护与控制, 2019, 47(6): 40-47.

谢小瑜, 周俊煌, 张勇军, 等. 基于W-BiLSTM的可再生能源超短期发电功率预测方法[J]. 电力系统自动化, 2021, 45(8): 175-184.

盛四清, 金航, 刘长荣. 基于VMD-WSGRU的风电场发电功率中短期及短期预测[J]. 电网技术, 2022, 46(3): 897-904.

PENG S M, ZHU J C, WU T Z, et al.Prediction of wind and PV power by fusing the multi-stage feature extraction and a PSO-BiLSTM model[J]. Energy, 2024, 298: 131345.

任东方, 马家庆, 何志琴, 等. 基于AVMD-CNN-GRU-Attention的超短期风功率预测研究[J]. 太阳能学报, 2024, 45(6): 436-443.

朱凌建, 荀子涵, 王裕鑫, 等. 基于CNN-BiLSTM的短期电力负荷预测[J]. 电网技术, 2021, 45(11): 4532-4539.

郭玲, 徐青山, 郑乐. 基于TCN-GRU模型的短期负荷预测方法[J]. 电力工程技术, 2021, 40(3): 66-71.

刘杰, 从兰美, 夏远洋, 等. 基于DBO-VMD和IWOA-BILSTM神经网络组合模型的短期电力负荷预测[J]. 电力系统保护与控制, 2024, 52(8): 123-133.

王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.

童宇轩, 金超, 李灿. 基于CEEMDAN-ISSA-BiLSTM的风电功率组合预测模型[J]. 电工电气, 2023(11): 26-32.

ABDEL-BASSET M, MOHAMED R, ABOUHAWWASH M.Crested porcupine optimizer: a new nature-inspired metaheuristic[J]. Knowledge-based systems, 2024, 284: 111257.

DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.

SAMAL K K R, PANDA A K, BABU K S, et al. Multi-output TCN autoencoder for long-term pollution forecasting for multiple sites[J]. Urban climate, 2021, 39: 100943.

GRAVES A.Long short-term memory[M]. Heidelberg: Springer, 2012: 37-45.

VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]//31st Conference on Neural Information Processing Systems (NIPS 2017). Long Beach, CA, USA, 2017.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于相似日聚类和WOA-VMD-TCN-Transformer模型的短期光伏功率研究

基于VMD-TCN-GRU-AM的超短期风电预测

SHORT-TERM WIND POWER FORECASTING BASED ON ATTENTION-GRU WIND SPEED CORRECTION AND STACKING

ADAPTIVE ULTRA-SHORT-TERM WIND SPEED PREDICTION MODEL CONSIDERING ERROR INFORMATION

ULTRA-SHORT-TERM WIND SPEED PREDICTION BASED ON INGO-SWGMN HYBRID MODEL

Related Author

赵丹阳

汤旭晶

汪恬

郭威

范竞敏

贺广林

王新刚

张奎

Related Institution

School of Electrical Engineering, Xi’an University of Technology

Xi’an Key Laboratory of Smart Energy,Xi’an University of Technology

School of Economics and Management, North China Electric Power University

Economic and Technology Research Institute, State Grid Chongqing Electric Power Company

College of Electrical Engineering & New Energy, China Three Gorges University

AI问答

⁰