基于Attention-ResNet-LSTM网络的中期负荷预测模型  

Medium-term Load Forecasting Model Based on Attention-ResNet-LSTM Network

作　　者：刘新志 刘爱莲[1,2] 李英娜 LIU Xin-zhi;LIU Ai-lian;LI Ying-na(Faculty of Information Engineering and Automation,Kunming University of Science and Technology;Yunnan Key Laboratory of Computer Technology Application,Kunming University of Science and Technology)

机构地区：[1]昆明理工大学信息工程与自动化学院 [2]昆明理工大学云南省计算机技术应用重点实验室

出　　处：《化工自动化及仪表》2021年第6期575-580,645,共7页Control and Instruments in Chemical Industry

摘　　要：提出一种基于Attention-ResNet-LSTM网络的中期负荷预测模型。将Attention机制引入LSTM模型,赋予不同的权重于特征向量,加入ResNet网络后算出负荷的预测值。以爱尔兰某地区的真实负荷为数据集进行仿真实验,负荷预测结果表明:相比于RNN、LSTM、Attention-LSTM模型,Attention-ResNet-LSTM模型的预测精度更高。In this paper,a medium-term load forecasting model based on Attention-ResNet-LSTM network was proposed,in which,having Attention mechanism introduced to LSTM model to put different weight on feature vector and then,having ResNet network adopted to calculate the predicted value of the load.Through having the real load data in Ireland taken to verify the validity of the model,the load prediction results show that,compared with RNN,LSTM and Attention-LSTM model,the Attention-ResNet-LSTM model has higher prediction accuracy.

关 键 词：中期负荷预测 电力负荷 LSTM网络 Attention机制 ResNet网络 

分 类 号：TP27[自动化与计算机技术—检测技术与自动化装置] TM744[自动化与计算机技术—控制科学与工程]