基于深度学习的变压器负载预测研究  

Study on Deep Learning-based Transformer Load Forecasting

作　　者：王文文 刘阳升 WANG Wenwen;LIU Yangsheng(Binzhou Power Supply Company,State Grid Shandong Electric Power Company,Binzhou 256600,China;Guilin University of Electronic and Technology,Guilin 541004,China)

机构地区：[1]国网山东省电力公司滨州供电公司,山东滨州256600 [2]桂林电子科技大学,广西桂林541004

出　　处：《电工技术》2024年第15期7-9,13,共4页Electric Engineering

摘　　要：随着以新能源为主体的新型电力系统快速发展,加之季节性负荷的增加,每年迎峰度夏、度冬、重大节假日期间的变压器重过载等问题也日益严重,严重影响变压器使用寿命和供电可靠性。通过负载预测提前对负载进行调整和转供,是解决变压器重过载问题的重要手段之一,因此实现变压器负载的准确预测至关重要。基于深度学习搭建长短期记忆循环神经网络(LSTM)的短期负荷预测模型,以变压器的历史负载、节假日信息及气象数据为输入,预测变压器负载水平。以两台容量为5000 kVA的35 kV变压器为例,通过MATLAB搭建负载预测模型,验证了变压器负载预测的准确性。With the rapid development of new power systems mainly consisted of renewable energy generations,coupled with the increase of seasonal loads,the problems of heavy/overload transformer during peak summer,winter and major holidays are becoming more and more serious every year,which seriously affects the service life of transformers and the reliability of power supply.One of the important means to solve the transformer heavy/overload problem is to adjust and transfer the load in advance by load forecasting,so it is crucial to achieve accurate prediction of transformer load.This study establishes a short-term load forecasting model based on long and short-term memory recurrent neural network(LSTM)with deep learning to forecast the load level of transformers in the coming week using the historical load of transformers,holiday information and meteorological data as input.The model′s accuracy in forecasting transformer load is verified on MATLAB using two 35 kV transformers with a capacity of 5000 kVA as an example.

关 键 词：深度学习 变压器 负载预测 气象数据 

分 类 号：TM72[电气工程—电力系统及自动化]