摘要
随着智能电网快速发展,用电信息采集系统中智能电能表规模日渐庞大,给海量数据实时分析及电能表运维带来巨大挑战。近年来,图形处理器(Graphics Processing Unit,GPU)超高速并行计算及快速训练大规模神经网络特性已经成为国内外高性能计算领域一个新的研究热点。但是,到目前为止,还没有看到GPU在用电信息采集系统中的应用。文章着重研究如何在用电信息采集系统中运用GPU实现电能表健康状态在线评估及预测,以提升统计性能,为电能表精益化运维提供有力依据。
With the rapid development of the smart grid,the scale of the intelligent energy meters in electricity information acquisition system is increasing day by day,which brings great challenge to the real-time analysis of massive data and operation and maintenance of electric energy meter.Recently,the highly data-parallel computing and rapidly training large-scale neural network of graphics processing unit(GPU)has been a new research hotspot in the field of high-performance parallel computing.However,until now,GPU has not been applied to electricity information acquisition system.In order to improve the performance of statistical analysis and realize the prediction of health status of electric energy meter,this paper focuses on the research how to realize GPU in electricity information acquisition system,to support the lean operation and maintenance of electric energy meter.
作者
陆春艳
陶晓峰
周赣
赵嘉豪
Lu Chunyan;Tao Xiaofeng;Zhou Gan;Zhao Jiahao(NARI Group Corporation,State Grid Electric Power Research Institute,Nanjing 211106,China;School of Electrical Engineering,Southeast University,Nanjing 210096,China)
出处
《电测与仪表》
北大核心
2020年第11期135-140,152,共7页
Electrical Measurement & Instrumentation
基金
国家电网公司总部科技项目(524609180077)。
关键词
图形处理器
径向基神经网络
电能表健康状态评估
电能表健康状态预测
graphics processing unit(GPU)
RBF neural network
health status assessment of electric energy meter
health status forecasting of electric energy meter
