考虑多变量建模的中期负荷预测模型  

Medium-Term Load Forecasting Model Considering Multivariate Modeling

作　　者：徐利美[1] 赵金 李裕民 姚非 邢吉伟 续欣莹 XU Limei;ZHAO Jin;LI Yumin;YAO Fei;XING Jiwei;XU Xinying(State Grid Shanxi Electric Power Company,Taiyuan 030000,China;Electric Power Research Institute,State Grid Shanxi Electric Power Company,Taiyuan 030001,China;Shanxi Electric Power Trading Center Co.,Ltd.,Taiyuan 030021,China;State Grid Taiyuan Power Supply Company,Taiyuan 030012,China;School of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]国网山西省电力公司,太原030000 [2]国网山西省电力公司电力科学研究院,太原030001 [3]山西电力交易中心有限公司,太原030021 [4]国网太原供电公司,太原030012 [5]太原理工大学电气与动力工程学院,太原030024

出　　处：《南方电网技术》2024年第11期79-87,共9页Southern Power System Technology

基　　金：国家重点研发计划资助项目(2017YFA0700304);山西省自然科学基金面上项目(20210302123189)~~。

摘　　要：中期负荷预测受温度、节假日和周末等多个外部变量影响。长短时记忆网络(long short-term memory,LSTM)虽然在短期负荷预测中展现了强大的预测能力,但不能很好地建立起中期负荷预测多外部变量与预测负荷之间的相关关系。针对上述问题,提出了并行LSTM结构以及时间序列N节点树形LSTM(time-series N-node tree-LSTMs, t-N Tree-LSTMs)结构,通过引入分支结构和树形结构构建更细的特征粒度实现对中期负荷预测的建模。最后在2017年全球能源预测大赛数据集GEFCom2017上进行实验,结果表明在中期负荷预测过程中更细的特征粒度有利于获取更高精度的预测结果,验证了并行LSTM模型和t-N Tree-LSTMs模型的有效性。Medium-term load forecasting is influenced by multiple external variables such as temperature,holidays,and weekends.Although long short-term memory(LSTM)networks have shown strong predictive ability in short-term load forecasting,they cannot establish a good correlation between multiple external variables and predicted load in medium-term load forecasting.To address the above issues,parallel LSTM structures and time series N-node tree LSTM(t-N Tree LSTM)structures are proposed.By introducing branch structures and tree structures to construct finer feature granularity,modeling of medium-term load forecasting is achieved.Finally,experiments are conducted on the 2017 global energy forecasting competition dataset GEFCom2017,and the results show that finer feature granularity is beneficial for obtaining higher accuracy prediction results in the medium-term load forecasting process,verifying the effectiveness of the parallel LSTM model and t-N Tree LSTMs model.

关 键 词：中期负荷预测 长短时记忆网络 时间序列 特征粒度 多变量建模 

分 类 号：TM73[电气工程—电力系统及自动化]