Ultra-short-term Wind Power Prediction Based on Deep Ensemble Learning Model Using Multivariate Mode Decomposition and Multi-objective Optimization
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.
wind power predictionmultivariate variational mode decomposition(MVMD)multi-objective crisscross op-timization(MOCSO)Blending ensemble learning
国家科技期刊平台
NSTL
万方数据
