基于NGO-VMD-FCBF-Informer的电力负荷组合预测模型

Powerload forecasting based on NGO-VMD-FCBF-Informer

电力负荷预测对电力系统安全稳定运行至关重要,现有的预测算法在精度及稳定性方面优化存在着欠缺,在此提出一种基于NGO-VMD-FCBF-Informer电力负荷组合预测模型。为提高原始数据的平稳性,使用VMD算法对原始数据进行分解,同时利用NGO算法对VMD的IMF分量层数及惩罚因子两个参数进行寻优。针对电力负荷预测受温度、电价等众多不确定性因素影响的问题,采用FCBF算法筛选出相关性程度高的特征变量作为输入变量。最后采用Informer网络对各个IMF分量进行单独预测,并对每个IMF分量预测结果进行重构叠加得到最终预测结果。同时,将该模型与其他预测模型进行对比实验分析,实验结果表明,该模型均值绝对误差、平均绝对百分比误差及均方根误差均低于列举的预测模型,能够有效地提高电力负荷的精度。

Power load forecasting is very important to the safe and stable operation of the power system.The existing forecasting algorithms are lacking in the optimization of accuracy and stability.Here,a power load forecasting model based on NGO-VMDFCBF-Informer is proposed.In order to improve the stationarity of the original data,the VMD algorithm is used to decompose the original data,and the NGO algorithm is used to optimize the two parameters of the VMD's IMF components and penalty factor.Aiming at the problem that the power load forecast is affected by many uncertain factors such as temperature and electricity price,the FCBF algorithm is used to screen out the characteristic information with high correlation degree as the input information.Finally,the Informer network is used to predict each IMF component separately,and the prediction result of each IMF component is reconstructed and superimposed to obtain the final prediction result.At the same time,the model is compared with other prediction models.The experimental results show that the mean absolute error,mean absolute percentage error and root mean square error of the model are lower than the listed prediction models,which can effectively improve the accuracy of power load.