基于数据隐私的工作流数据布局

Placement of Workflow and Data Based on Data Privacy

随着信息采集设备及技术的迅速发展,各行业部门的海量数据逐渐具有大数据特征,而传统的“单机”数据处理方式已经渐渐不能够满足数据处理的“实时性”等要求,因此,基于“云计算”强大的性能优势,各行业部门集中已有的“计算”和“存储”资源建立“集群”以处理海量数据。但是,云计算虽然提高各类应用的计算速度,但是各节点之间的数据传输也产生额外的数据传输时间。同时,随着数据保密性要求的提高,部分隐私冲突数据应避免放置在相同或者邻近节点上,以保证数据的安全性。因此,针对这一挑战,提出一种工作流和数据的协同布局方法,以共同优化数据访问时间和隐私数据冲突度。

With the rapid development of information collection equipment and technology,the massive data of various industry sectors gradually has the characteristics of big data,the traditional single machine data processing method has gradually failed to meet the requirements of realtime data processing.Therefore,based on the powerful performance advantages of cloud computing,various industry departments centralize existing computing and storage resources to establish cluster to handle massive data.However,although cloud computing has increased the speed of calculations for various applications,but the data transmission between nodes also generates extra data transmission time.At the same time,as data privacy requirements increase,partial privacy conflict data should be avoided on the same or neighboring nodes to en⁃sure data security.Therefore,for this challenge,proposes a collaborative layout method for workflow and data to jointly optimize data ac⁃cess time and privacy data conflict.