基于可控关联性网络的大数据群体计算任务分配方法  

Research on Task Allocation Method of Large Data Group

作　　者：周晓娟[1] ZHOU Xiaojuan(Henan Institute of Economics and Trade,Zhengzhou Henan 450000,China)

机构地区：[1]河南经贸职业学院,河南郑州450000

出　　处：《信息与电脑》2023年第17期186-188,共3页Information & Computer

摘　　要：传统大数据群体计算任务分配方法以任务分配的增益为主,在任务添加、分配冲突、二次分配的阶段增加了多次计算,影响任务分配效率。针对此问题,设计基于可控关联性网络的大数据群体计算任务分配方法。首先,确认可控关联性网络大数据群体分配权限,获取自适应分割子任务,建立子任务之间的关联度,使任务能够分配到关联度更高的用户。其次,建立大数据群体计算任务的合理分配机制,将发布方提交的任务进行预处理,接收方根据任务关联度进行任务分配。最后,进行实验分析。实验结果表明,该方法的分配效果更佳,优于对照组。The traditional big data group computing task allocation method mainly focuses on the gain of task allocation,adding multiple calculations during the stages of task addition,allocation conflicts,and secondary allocation,which affects the efficiency of task allocation.To address this issue,a task allocation method for big data group computing based on controllable correlation networks is designed.Firstly,confirm the controllable relevance of network big data group allocation permissions,obtain adaptive segmentation subtasks,establish the correlation between subtasks,and enable tasks to be assigned to users with higher correlation.Secondly,establish a reasonable allocation mechanism for big data group computing tasks,preprocess the tasks submitted by the publisher,and assign tasks to the recipient based on task correlation.Finally,conduct experimental analysis.The experimental results show that the allocation effect of this method is better than that of the control group.

关 键 词：可控关联性网络 大数据群体 计算任务 分配方法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]