基于TabNet-LSTNet的多特征短期负荷预测  

Multi-featured short-term load forecasting based on TabNet-LSTNet

作　　者：吴文辉 何家峰[1] 蔡高琰 骆德汉[1] WU Wenhui;HE Jiafeng;CAI Gaoyan;LUO Dehan(School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,P.R.China;Guangdong Haodi Innovation Technology Co.,Ltd.,Foshan,Guangdong 528200,P.R.China)

机构地区：[1]广东工业大学信息工程学院,广州510006 [2]广东浩迪创新科技有限公司,广东佛山528200

出　　处：《重庆大学学报》2024年第9期129-140,共12页Journal of Chongqing University

基　　金：国家自然科学基金资助项目(61571140)。

摘　　要：为了挖掘负荷预测中不同输入特征的重要性,有效处理负荷数据中的线性成分和非线性成分,提高负荷预测的精度,提出一种基于TabNet和长期和短期时间序列网络(long and short-term temporal networks,LSTNet)的组合负荷预测模型。通过引入自监督预训练来提高TabNet的预测精度,通过训练得到输入特征的全局重要性和预测结果,然后把重要性高的特征输入到LSTNet训练得出预测结果,最后通过方差-协方差组合方法得出TabNet-LSTNet模型的预测结果。通过仿真分析,与传统的长短期记忆网络(long short-term memory,LSTM)、极端梯度提升机(extreme gradient boost,Xgboost)、轻量级梯度提升机(lignt gradient boosting machine,Lightgbm)和其他组合模型相比较,TabNet-LSTNet模型具有更高的精度。To explore the importance of different input features in load forecasting,effectively handle the linear and nonlinear components in load data,and improve the accuracy of load prediction,a combined load prediction model based on TabNet and LSTNet(long and short-term temporal networks)is proposed in this paper.First,the prediction accuracy of TabNet is improved by introducing self-supervised pre-training,and then the global importance of the input features and the prediction results are obtained by training.Next,the features with high importance are input to LSTNet,which is trained to obtain the prediction results.Finally,the prediction results of the combined model are derived using the variance-covariance combination method.Simulation analysis shows that the proposed combined model has higher accuracy compared with traditional LSTM(long and short-term memeory),Xgboost(extreme gradient boost),Lightgbm(lignt gradient boosting machine)and other combined models.

关 键 词：负荷预测 特征重要性 TabNet 自监督预训练 LSTNet 

分 类 号：TM715[电气工程—电力系统及自动化]