基于VMD-LSTM的短期电力负荷预测研究  

Research on Short Term Load Forecasting Based on VMD-LSTM

作　　者：黄志祥 周莉[1] HUANG Zhixiang;ZHOU Li(School of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001

出　　处：《洛阳理工学院学报（自然科学版）》2022年第3期76-80,96,共6页Journal of Luoyang Institute of Science and Technology：Natural Science Edition

基　　金：安徽理工大学2020研究生创新基金项目(2020CX2059).

摘　　要：为了提高短期电力负荷预测的精准度,提出一种基于变分模态分解(VMD)和长短期记忆网络(LSTM)相结合的组合型预测模型。利用VMD将原始负荷样本集分解为多个不同的本征模函数(IMF)和一个剩余分量,以降低负荷数据样本集的非平稳性和复杂度,用LSTM模型对分解得到的多个子模态分量分别进行预测,对不同分量的预测结果进行叠加,得到最终负荷预测值。通过仿真实验,对比VMD-LSTM模型、BP模型、ELM模型和LSTM的预测结果,VMD-LSTM模型的预测效果优于其他3种预测模型,在短期电力负荷预测方面表现出良好的性能。In order to improve the accuracy of short-term electric load forecasting,a combined forecasting model is proposed based on the combination of variational modal decomposition(VMD)and long short-term memory network(LSTM).First,VMD is used to decompose the load sample set sequence into several different eigenmode functions(IMFs)and one remaining component,to reduce the non-smoothness and complexity of the load data sample set;then,the LSTM model is used to predict the decomposed sub-modal components separately;finally,the prediction results of different components are superimposed to obtain the final load prediction value.Through simulation experiments,the prediction results of the LSTM model BP and ELM models were compared and analysed.The results show that the VMD-LSTM model outperforms the other three prediction models and exhibits good performance in short-term power load forecasting.

关 键 词：短期电力负荷预测 固有模态分量 VMD 降噪 LSTM 

分 类 号：TM715[电气工程—电力系统及自动化] TP311.5[自动化与计算机技术—计算机软件与理论]