电子器件2025，Vol.48Issue(2)：432-438,7.DOI:10.3969/j.issn.1005-9490.2025.02.030
基于CEEMD-SE和TCN-LSTM组合神经网络的超短期负荷预测
Ultra-Short-Term Load Forecasting Based on CEEMD-SE and TCN-LSTM Combined Neural Network
摘要
Abstract
The original load data have the features of volatility and randomness,which make it difficult to improve the accuracy of load forecasting.In order to improve the accuracy of load forecasting,an ultra short term load forecasting method based on CEEMD-SE and TCN-LSTM combined neural network is proposed,and the corresponding forecasting model is constructed.Firstly,the original load se-quence is decomposed into several intrinsic mode function(IMF)components and a residual(Res)component through complementary set empirical mode decomposition(CEEMD),and the similar components are reconstructed by using sample entropy(SE)algorithm.Sec-ondly,time convolution network(TCN)is selected as the feature pre extraction module of load data,and long short-term memory(LSTM)network is selected as the prediction module to build TCN-LSTM combined forecasting model.Finally,the feasibility of improving the prediction accuracy of the model is verified by an example.The results show that the average absolute error(MAE),root mean square error(RMSE)and average absolute percentage error(MAPE)of the proposed model are 38.296 WM,30.929 WM and 0.472%respec-tively.Compared with the traditional model,the prediction error is smaller.关键词
负荷预测/互补集合经验模态分解/时间卷积网络/长短期记忆网络/样本熵Key words
load forecasting/complementary ensemble empirical mode decomposition/time convolution network/long short-term memory network/sample entropy分类
信息技术与安全科学引用本文复制引用
冯汉中,詹鹏,区伟健,张卫华,黄启文..基于CEEMD-SE和TCN-LSTM组合神经网络的超短期负荷预测[J].电子器件,2025,48(2):432-438,7.基金项目
南方电网科技项目(080016KK52200004) （080016KK52200004）
