一种基于维层次聚集树的Cube增量更新算法  

Novel Incremental Update Algorithm of the Cube Based on Dimension Hierarchy Aggregate Tree

作　　者：胡孔法[1] 陈崚[1] 董逸生[2] 

机构地区：[1]扬州大学计算机科学与工程系,江苏扬州225009 [2]东南大学计算机科学与工程系,江苏南京210096

出　　处：《小型微型计算机系统》2005年第12期2126-2130,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60473012)资助;国家"十五"重大科技攻关项目(2003BA614A)资助;江苏省"十五"高科技项目(BG2004034)资助.

摘　　要：提出利用Cube中的维层次聚集树(d im ens ion h ierarchy aggregate tree,简称DHA_T ree)来对聚集Cube进行增量更新维护,在维层次聚集Cube中进行数据插入和删除等数据更新时,充分利用维层次聚集树中的维层次前缀,由下向上用更新前后的差值对受到更新结点影响的所有祖先结点进行增量更新.在插入新维数据时,在不需要重新构建聚集Cube就可以对聚集Cube进行增量更新,从而减少了Cube的更新时间.对基于维层次聚集树的聚集Cube与传统Cube进行了算法性能分析和比较,结果表明本文所提出的聚集Cube的增量更新算法性能最佳.The paper proposes a novel incremental update algorithm to update the aggregate cube with the dimension hierarchy aggregate tree on the cube, By using the hierarchical prefix of the dimension hierarchy aggregate tree, the aggregate cube can incrementally update the all affected ancestor notes while updating the data cell in it, The aggregate cube can also incrementally update without being recreated while being added new dimension data in it. As a result, this algorithm can greatly reduce the update time, We have compared the algorithms of the aggregate cube based on dimension hierarchy aggregate tree with the existed other ones such as DDC（dynamic data cube） , The results show that the algorithms of the aggregate cube proposed in this paper are more efficient than other existed ones.

关 键 词：维层次聚集树 增量更新 维层次前缀 多维联机分析处理 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]