Short-term Wind Speed Prediction Based on VMD-PSO-ELM Model with Error Correction
ZHAI Chenchen
LI Hanlin
YU Min
WEI Lai
Abstract：The nonstationarity and randomness of wind speed series lead to inaccurate wind speed prediction.This paper pres-ents a wind speed prediction model based on the combination of variational mode decomposition(VMD),particle swarm optimiza-tion algorithm(PSO),extreme learning machine(ELM)and long short-term memory network(LSTM).Firstly,the original wind speed sequence is decomposed into a series of eigen mode components from low frequency to high frequency using the VMD algo-rithm.Each component is predicted by the ELM.For the randomness of weights and thresholds generated by the ELM,the model re-sults are unstable.PSO is used to find the best parameter combination of weights and thresholds to improve the performance of the model.Aiming at the error sequence between the original wind speed series and the integrated series,LSTM model is used to modify the error sequence,then the integrated series is added to obtain the final prediction value.This paper uses two sets of data sets from the US national wind farm as a case study.The experimental results show that,compared with other benchmark models,the model has advantages in short-term wind speed prediction.
Keywords：VMD algorithmPSOELMLSTMshort-term wind speed prediction
Publication Date：2025-06-20
Online Publishing Date：2025-09-23(First online date of this platform, not the publication date of the document)
Pages：7( 1557-1563 )