基于无限深度神经网络的电能信息计量方法

Electric Energy Information Measurement Method Based on Infinite Depth Neural Network

针对现有技术电能计量资产信息繁多、管理滞后的问题,提出一种电能信息计算方法,这种方法能在物联网络内随时随地实现电能计量信息的计算与处理,提高数据即时性,并构建出大数据挖掘算法,实现不同阶段、不同数据信息的分析与挖掘。通过构建出无限深度神经网络模型,将不同生命周期的电能计量资产数据有机融合在一起,实现不同种类数据的挖掘、融合、计算和分析,提高资产数据管理的能力。试验表明,所提出的方法数据挖掘能力强,准确度高,高达92%以上。

Aiming at the problems of a large amount of information and lagging management of electric energy metering assets in the prior technologies,a new method is proposed such that the calculation and processing of electric energy metering information can be realized anytime and anywhere within the Internet of Things,which improves the ability of real-time data calculation,and builds big data mining algorithms to achieve different analysis and mining of different data.By constructing an infinitely deep neural network,the energy metering asset data of different life cycles are organically integrated,the mining,fusion,calculation and analysis of different types of data are realized,and the ability of asset data management is improved.Experiments show that the method proposed has strong data mining ability and high accuracy which is as high as 92%.