智能电网大数据去隐私化加密提取模型构建

Construction of De-privacy Encryption Extraction Model for Big Data in Smart Grid

针对传统智能电网大数据去隐私化加密提取模型存在提取精度不足的问题,文章在数据挖掘的基础上,构建了新的智能电网大数据去隐私化加密提取模型。该模型的构建主要分为2个阶段:第一阶段,利用协同认知模型对智能电网大数据进行去隐私化解密处理;第二阶段,首先对去隐私化解密后数据进行预处理,包括数据清洗、数据归约、数据标准化等,然后利用遗传神经算法提取数据聚类中心,最后计算数据集与聚类中心之间的相似性,筛选出最大相似性的数据,从而实现数据提取。结果表明:与其他3种基于分类的提取模型相比,本模型提取出的数据量与原始数据集中符合条件的数据量一致,由此可见本模型的提取精度更高。

Aiming at the problem of insufficient extraction accuracy of traditional big data de-privacy encryption extraction model in smart grid, a new model of big data de-privacy encryption extraction in smart grid is constructed on the basis of data mining. The construction of this model can be divided into two stages: the first stage is the de-privacy and decryption of big data in smart grid using cooperative cognitive model;the second stage is the pre-processing of big data in smart grid after de-privacy and decryption, including data cleaning, data reduction, data standardization, etc. Then the genetic neural algorithm is used to extract data clustering centers, and finally the similarity between data sets and clustering centers is computed, and the data with the greatest similarity is selected, so as to achieve data extraction. The results show compared with the other three classified data extraction models based on de-privacy encryption, the amount of data extracted by this model is consistent with the amount of data in the original data set, which shows that the extraction accuracy of this model is higher.