首页|基于数据流聚类的多任务并行数据控制方法

基于数据流聚类的多任务并行数据控制方法

扫码查看
多任务并行数据的类别较多、数据流庞大,导致其控制能力较差,增加了物联网访问负担和通信开销.为了提升数据流稳定性,规范数据流访问过程,提出基于数据流聚类算法的多任务并行数据控制方法.首先利用数据采集与监视系统,从识别、采集、验证三个方面获取物联网数据流;然后计算各数据流动态趋势间的欧氏距离,使数据流相似度衡量标准统一;将优化后数据流代入聚类算法中,根据数据流时间戳合理对应任务请求;最后利用PLC控制器实现多任务并行数据控制.实验结果表明,所提方法的可扩展性高、加速比高.
Multitasking data control method based on data stream clustering
Various types of multitasking data and huge data stream have led to poor control ability and in-crease the access burden and communication overhead of the Internet of Things.In order to improve data stream stability and standardize data stream access process,a multitasking data control method based on da-ta stream clustering algorithm is proposed.Firstly,the data collection and monitoring system is used to ob-tain the data stream of the Internet of Things from the three aspects of identification,collection and verifica-tion.Then,the Euclidean distance between the dynamic trends of each data stream is calculated to make the measurement standard of data stream similarity uniform.The optimized data stream is substituted into the clustering algorithm,and reasonably correspond to the task request according to the timestamp of the da-ta stream.Finally,the PLC controller is used to realize multitasking data control.The experiment results show that the proposed method has high scalability and high speedup ratio.

data acquisition and monitoring systemdata stream preprocessingsimilarity measurement standardclustering algorithmPLC controller

张嘉慧、陈智明、黄科、王晓琪、李子龙

展开 >

广东电网有限责任公司梅州供电局,广东 梅州 514021

数据采集与监视系统 数据流预处理 相似度衡量标准 聚类算法 PLC控制器

国家级新一代人工智能科技项目

2020AAA0103400

2024

信息技术
黑龙江省信息技术学会 中国电子信息产业发展研究院 中国信息产业部电子信息中心

信息技术

CSTPCD
影响因子:0.413
ISSN:1009-2552
年,卷(期):2024.(3)
  • 11