吉首大学学报（自然科学版）2026，Vol.47Issue(1)：41-48,8.DOI:10.13438/j.cnki.jdzk.2026.01.007
基于VMD-CNN-BiLSTM-RF模型的短期光伏发电功率预测
Short-Term Photovoltaic Power Prediction Based on VMD-CNN-BiLSTM-RF
摘要
Abstract
In response to the non-stationary nature and noise interference caused by weather affected pho-tovoltaic power generation,as well as the spatiotemporal coupling effect,a short-term power prediction composite model VMD-CNN-BiLSTM-RF based on Variational Mode Decomposition(VMD),Convolu-tional Neural Network(CNN),Bi-directional Long Short-Term Memory(BiLSTM),and Random Forest(RF)is proposed.This model uses VMD to decompose the original power sequence into multiple station-ary sub-modes,reducing the impact of noise and non-stationarity.It combines CNN with BiLSTM to sim-ultaneously capture spatial features and temporal dependencies of time series data,improving the accura-cy of predictions.RF is integrated with sub-model prediction results to enhance the model's generalization ability.An experimental environment was set up on the Matlab platform to conduct comparative experi-ments and error analysis for the VMD-CNN-BiLSTM-RF combined model.The results show that this model has significantly improved the accuracy and robustness of short-term photovoltaic power genera-tion prediction.关键词
光伏发电/功率预测/变分模态分解/卷积神经网络/双向长短期记忆网络/随机森林Key words
photovoltaic power/generation prediction/variational mode decomposition/convolutional neu-ral network/bidirectional long-term and short-term memory network/random forest分类
信息技术与安全科学引用本文复制引用
李立..基于VMD-CNN-BiLSTM-RF模型的短期光伏发电功率预测[J].吉首大学学报（自然科学版）,2026,47(1):41-48,8.基金项目
安徽省高校自然科学研究重点项目(2024AH051153,2023AH053075) （2024AH051153,2023AH053075）
