风电数据标准化技术及风电大数据应用方法  

Wind Power Data Standardization Technology and Wind Power Big Data Application Method

作　　者：谭建鑫[1] 谢前 井延伟 赵晓楠 李鹏飞 TAN Jianxin;XIE Qian;JING Yanwei;ZHAO Xiaonan;LI Pengfei(Hebei Construction Investment New Energy Co.,Ltd.,Shijiazhuang 050051,China;Beijing Goldwind Smart Energy Technology Co.,Ltd.,Beijing 100176,China;Hebei Suntien New Energy Technology Co.,Ltd.,Zhangjiakou 075000,China)

机构地区：[1]河北建投新能源有限公司,河北石家庄050051 [2]北京金风慧能技术有限公司,北京100176 [3]河北新天科创新能源技术有限公司,河北张家口075000

出　　处：《微型电脑应用》2023年第2期89-92,96,共5页Microcomputer Applications

摘　　要：为了解决风电系统中多源异构数据类型不一致的问题,研究建立企业仓库和大数据平台系统,基于分布式架构实现并行查询和分析引擎,实现海量风电数据分布式存储和计算。大数据平台提供基于Mapreduce、Spark等技术的多种大数据计算引擎,支持Java、Scala、R、Python等多种语言,应内嵌常用算法库。采用Rational Rose建模工具建立风电数据标准化模型,建立具有层级关系的风电数据类的结构。使用IEC61400-25的信息模型与不同的业务系统数据通讯及系统整合,基于数据库的频繁项集挖掘和关联规则学习的Apriori算法完成频繁项集挖掘任务。实验结果显示,本研究数据处理加速度可达到16,数据标准化效率较高。In order to solve the inconsistency of multi-source heterogeneous data types in wind power systems, this research establishes an enterprise warehouse and big data platform system, implements parallel query and analysis engines based on a distributed architecture, and realizes distributed storage and calculation of massive wind power data. The big data platform provides multiple big data computing engines based on Mapreduce, Spark and other technologies, supports multiple languages such as Java, Scala, R, Python, etc., and has embedded common algorithm libraries. We use the rational rose modeling tool to establish a wind power data standardization model, and establish a hierarchical structure of wind power data classes. We also use IEC61400-25 information model and different business system data communication and system integration, based on the database of frequent itemsets mining and association rule learning Apriori algorithm to complete frequent itemsets mining tasks. The experimental results show that the data processing acceleration of this study can reach 16, and the data standardization efficiency is higher.

关 键 词：数据标准化体系 大数据平台系统 标准化模型 信息模型 频繁项集挖掘 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]