基于聚类算法的高速连续数据流并行处理控制系统设计  

Design of clustering algorithm based parallel processing control system for high⁃speed continuous data stream

作　　者：刘敏[1] 黄维[2] 兰诗梅[1] LIU Min;HUANG Wei;LAN Shimei(College of Mathematics and Information Science,Guiyang University,Guiyang 550005,China;Guizhou Provincial Water Conservancy Research Institute,Guiyang 550001,China)

机构地区：[1]贵阳学院数学与信息科学学院,贵州贵阳550005 [2]贵州省水利科学研究院,贵州贵阳550001

出　　处：《现代电子技术》2020年第13期114-118,共5页Modern Electronics Technique

基　　金：贵州省教育厅青年科技人才成长项目(黔教合KY字[2017]240);贵州省科技厅学术新苗项目(GYU⁃KJT[2019]⁃19);贵阳市科技局贵阳学院专项资金资助(GYU⁃KYZ[2018]04)。

摘　　要：传统的高速连续数据流并行处理控制系统运行过程中相对误差大,消耗内存高,为了解决这一问题,基于聚类算法设计了一种新的高速连续数据流并行处理控制系统。所提出的系统由功能层、数据源、接口层、数据层、资源层、应用层组成系统硬件结构,通过数据的获取、预处理、聚类处理和类别预测四步完成软件流程,软件在运行过程中需要应用聚类算法。为检验控制系统效果,与传统控制系统进行实验对比,结果表明,基于聚类算法设计的高速连续数据流并行处理控制系统在运行过程中相对误差极小,占用的内存少,系统运行效率高,并行处理控制效果好。The traditional parallel processing control system for high⁃speed continuous data stream has large relative error and high memory consumption.In order to solve this problem,a new parallel processing control system for high⁃speed continuous data stream is designed based on clustering algorithm.The hardware structure of the proposed system is composed of function layer,data source layer,interface layer,data layer,resource layer and application layer.The software flow is completed in four steps:data acquisition,pre⁃processing,clustering processing and classification prediction.The software needs to apply clustering algorithm in the running process.In order to test the effect of the control system,it was compared with the traditional control system in some experiments.The results show that the high⁃speed continuous data stream parallel processing control system designed on the basis of clustering algorithm has minimal relative error,high operating efficiency and good parallel processing control effect,and occupies less memory.

关 键 词：控制系统设计 聚类算法 数据流并行处理 聚类分析 参数设置 对比实验 

分 类 号：TN876-34[电子电信—信息与通信工程] TP301[自动化与计算机技术—计算机系统结构]