Research on short-term photovoltaic power generation prediction based on ICEEMDAN-LSTM-SSA
CHEN Hongbo
KANG Yu
WANG Liang
LIU Rui
HUA Xin
Abstract：A short-term photovoltaic power generation prediction model based on adaptive noise complete ensemble empirical mode decomposition-long short-term memory network-sparrow search algorithm(ICEEMDAN-LSTM-SSA)is proposed.Taking a certain photovoltaic power station in Bohu County,Baotou City,Xinjiang as the research object,the influence of different climate conditions on the prediction accuracy is analyzed.The research shows that using the ICEEMDAN decomposition algorithm to preprocess the power generation sequence can effectively improve the prediction accuracy of the LSTM model for photovoltaic power generation,the ICEEMDAN-LSTM-SSA prediction model demonstrates obvious universality under different climate conditions,and the prediction results are more accurate.
Keywords：photovoltaic power generationpower predictionLSTM neural networkmode decomposition
Publication Date：2026-01-31
Online Publishing Date：2026-03-11(First online date of this platform, not the publication date of the document)
Pages：5( 19-23 )