电力中台海量数据跨域快速检索方法设计  

Design of cross-domain fast retrieval method for massive data of power middle office

作　　者：王娅云 李增伟 魏永瑜 张译 马英辉 WANG Ya-yun;LI Zeng-wei;WEI Yong-yu;ZHANG Yi;MA Ying-hui(State Grid Qinghai Electric Power Company Information and Communication Company,Xining 810000,China)

机构地区：[1]国网青海省电力公司信息通信公司,西宁810000

出　　处：《信息技术》2025年第3期151-156,162,共7页Information Technology

摘　　要：以往的电力中台海量数据跨域快速检索方法效率不高,因此设计了电力中台海量数据跨域快速检索方法。采集电力中台的不同数据,并对其预处理,提取出数据的跨域特征,计算确定数据的聚类中心。分别计算域内、域间、域外的数据损失函数,完成数据的分类。基于此,计算目标数据和数据库数据间的相似度,输出相应的数据检索结果,完成电力中台海量数据的跨域快速检索。在实验测试中和以往的电力中台海量数据跨域快速检索方法相比,设计的电力中台海量数据跨域快速检索方法最小检索时间仅为0.23ms,检索效率较高。The efficiency of cross-domain fast retrieval of massive data of power station is not high in the past.Therefore,a fast cross-domain retrieval method for massive data of power middle office is designed.Different data of power center is collected and preprocessed to extract the cross-domain characteristics of data,and calculate and determine the clustering center of data.The data loss functions within,between and outside the domain are calculated respectively to complete the data classification.Based on this,the similarity between the target data and the database data is calculated,the corresponding data retrieval results are output,and the cross-domain fast retrieval of the massive data of the power middle office is completed.In the experiment test,compared with the previous cross-domain fast retrieval method of massive data in middle office station,the minimum retrieval time of the designed cross-domain fast retrieval method is only 0.23ms,and the retrieval efficiency is higher.

关 键 词：电力中台 跨域检索 聚类中心 数据损失函数 数据相似度 

分 类 号：TM73[电气工程—电力系统及自动化] TP391.1[自动化与计算机技术—计算机应用技术]