基于N-BEATS的能源互联网短期负荷预测  

Short⁃term load forecasting for energy internet based on N-BEATS

作　　者：尹浩然 张玲华[2] YIN Haoran;ZHANG Linghua(College of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;Jiangsu Engineering Research Center of Communication and Network Technology,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学物联网学院,江苏南京210003 [2]南京邮电大学江苏省通信与网络技术工程研究中心,江苏南京210003

出　　处：《电子设计工程》2024年第11期76-81,共6页Electronic Design Engineering

基　　金：太阳能高效利用及储能运行控制湖北省重点实验室开放基金(HBSEES202113)。

摘　　要：短期负荷预测在能源互联网的规划中既占重要组成部分,又是能源系统可靠高效运行的基础。在能源互联网中能源的短期负荷预测精度问题是人们重点关注问题。N-BEATS的深度神经结构未使用时序特别组成成分,仅使用一种基于后向和前向残差链路以及非常深的全连接层堆栈的深度神经架构。该结构具有可解释性、适用于广泛的目标域、并且训练速度快等优点。实验使用N-BEATS模型对历史负荷数据进行训练,然后对未来负荷进行短期负荷预测,取得了较高的预测精度。测得平均绝对百分比误差(eMAPE)为1.26%,平均绝对误差(eMAE)为84.238 kW,决定系数(R^(2))为0.9955,实验结果表明采用该方法的预测精度高于传统的预测方法,如在eMAPE方面相比TCN降低了0.61%。Short⁃term load forecasting not only plays an important part in the planning of Energy Internet,but also is the basis for reliable and efficient operation of energy systems.In the Energy Internet,the accuracy of energy short⁃term load forecasting is the focus of people’s attention.The deep neural architecture of N-BEATS does not use timing⁃specific components,but only uses a deep neural architecture based on backward and forward residual links and very deep fully connected layer stacks.The structure has the advantages of interpretability,applicability to a wide range of target domains,and fast training speed.In the experiment,N-BEATS model is used to train historical load data,and then short⁃term load forecasting is carried out for future load,with high forecasting accuracy.The measured mean absolute percentage error(eMAPE)is 1.26%,the mean absolute error(eMAE)is 84.238 kW,and determination coefficient(R^(2))is 0.9955.The experimental results show that the prediction accuracy of this method is higher than that of traditional prediction methods,for example,in terms of eMAPE,Reduced by 0.61%compared to TCN.

关 键 词：能源互联网 短期负荷预测 N-BEATS网络模型 深度学习 时间序列 

分 类 号：TN919.5[电子电信—通信与信息系统]