摘要
针对电力负荷序列的非平稳、非线性和长记忆等问题,建立了一种基于变分模态分解(VMD)、考虑变分模态分解残差量情况的长短期记忆神经网络(LSTM)电力负荷预测模型。首先,该预测模型采用VMD算法将归一化后的电力负荷数据分解为一系列本征模态(IMF)分量和残差量;然后,对每个IMF和残差量分别建立LSTM模型进行预测;最后,将各分量预测结果反归一化组合重构得到最终的电力负荷预测结果。使用平均绝对百分误差(MAPE)和均方根误差(RMSE)评价模型,结果表明该模型的预测精度优于LSTM模型和VMD-LSTM模型。
Based on the characteristics of non-smooth,nonlinear and long memory of power load sequence,a power load forecasting model based on variational mode decomposition(VMD),considering VMD decomposition residuals and long short-term memory neural network(LSTM)is proposed.First,the method used the VMD algorithm to decompose the normalized power load data into a series of intrinsic mode function components and residuals.Then,the LSTM forecasting model was established for each IMF and the residuals.Finally,the component forecasting results were reconstructed to achieve the final load forecasting.The model is evaluated using Mean Absolute Percentage Error(MAPE)and Root Mean Square Error(RMSE).The results show that the model outperform the LSTM model and VMD-LSTM model in terms of forecasting accuracy.
作者
张莲
李涛
宫宇
杨洪杰
张尚德
贾浩
ZHANG Lian;LI Tao;GONG Yu;YANG Hongjie;ZHANG Shangde;JIA Hao(Chongqing Energy Internet Engineering Technology Research Center,Chongqing 400054,China;School of Electrical and Electronic Engineering,Chongqing University of Technology,Chongqing 400054,China)
出处
《重庆理工大学学报（自然科学）》
CAS
北大核心
2022年第1期165-170,共6页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金项目(61976030)。
关键词
电力负荷预测
变分模态分解
长短期记忆神经网络
机器学习
power load forecasting
variational mode decomposition
long short-term memory neural network
machine learning
