现代电力2024，Vol.41Issue(3)：458-469,12.DOI:10.19725/j.cnki.1007-2322.2022.0318
基于多元模态分解与多目标算法优化的深度集成学习模型的超短期风电功率预测
Ultra-short-term Wind Power Prediction Based on Deep Ensemble Learning Model Using Multivariate Mode Decomposition and Multi-objective Optimization
摘要
Abstract
To address the issue of ultra-short-term wind power prediction,a novel prediction model is proposed based on mul-tivariate variational mode decomposition(MVMD),multi-ob-jective crisscross optimization(MOCSO)algorithm and blend-ing ensemble learning.In the data processing stage,to maintain synchronization correlation and ensure matching of intrinsic mode fuctions(IMFs)number and frequency,the MVMD method is used to decompose the multi-channel original data synchronously.Considering the insufficient comprehensive-ness,inaccuracy,and low robustness of the single machine learning model,a blending ensemble learning model is pro-posed to combine multiple deep learning networks using MOC-SO dynamic weighting.The prediction results of RNN,CNN and LSTM are dynamically weighted,integrated,and then op-timized by MOCSO to improve the prediction accuracy and sta-bility.Experimental results show that the proposed model is not only effective,but also significantly superior to other predic-tion models.关键词
风电功率预测/多元变分模态分解/多目标纵横交叉优化/Blending集成学习Key words
wind power prediction/multivariate variational mode decomposition(MVMD)/multi-objective crisscross op-timization(MOCSO)/Blending ensemble learning分类
信息技术与安全科学引用本文复制引用
朱梓彬,孟安波,欧祖宏,王陈恩,张铮,陈黍,梁濡铎..基于多元模态分解与多目标算法优化的深度集成学习模型的超短期风电功率预测[J].现代电力,2024,41(3):458-469,12.基金项目
国家自然科学基金项目(61876040).Project Supported by National Natural Science Foundation of China(61876040). （61876040）
