摘要
在大数据技术发展了十年、物联网技术日趋完善的背景下,很多企业坐拥大量数据,希望能够实现数据驱动的决策,进而实现精细化运营,以提高运营效率,减少不必要的成本,并增加企业利润。这个过程离不开对高质量数据的积累、存储、分析、挖掘和建模。本文基于若干风力发电厂在数据挖掘项目中的某些数据质量问题展开讨论,分析了数据质量在不同方面对模型效果的影响。
With ten years’development of big data technology as well as the increasing perfection of Internet of Things,many enterprises possessing a mass of data hope to realize data-driven decision,and then,achieve refined operation,improve its operating efficiency,reduce unnecessary cost and increase corporate profits.This process cannot be achieved without the accumulation,storage,analysis,digging and modeling of high quality data.This article discusses some data quality problem in data-digging project of wind power plants,and analyze the effects of data quality on model effect in many ways.
作者
潘肖宇
郭鹏程
张广斌
王大鹏
赵磊
陈勤元
PAN Xiaoyul;GUO PengchengZHANG Guangbin;WANG Dapeng;ZHAO Lei;CHEN Qinyuan(HYDROCHINA CORPORATION,Beijing 100000,China;Beijing Qingyide Technology Co.,Ltd.Beijing 100041,China;Sinohydro wind power Zhangbei Co.,Ltd,Zhangjiakou 076400,China)
出处
《风力发电》
2019年第3期59-65,58,共8页
Wind Power
关键词
大数据
数据驱动的决策
风力发电
数据质量
数据治理
big data
data-driven decisions
wind power generation
data quality
data management