数据仓库系统中一种改进的维层次聚集Cube存储结构  

An Improved Dimension Hierarchy Aggregate Cube Storage Structure for Data Warehouses

作　　者：梁作鹏[1] 胡孔法[1] 董逸生[1] 陈崚[2] 

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

出　　处：《计算机研究与发展》2005年第8期1362-1368,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60473012);国家"十五"重大科技攻关基金项目(2003BA614A);国家"八六三"高技术研究发展计划基金项目(2002AA231071);江苏省"十五"高科技基金项目(BG2004034;BG2001013)

摘　　要：提出利用Cube中的维层次(dimensionhierarchy)聚集技术来创建高性能的维层次聚集Cube(dimensionhierarchyaggregatecube,DHAC).充分利用DHAC已保存的维层次信息,对Cube中多维数据的查询和更新效率进行了优化,并且支持Cube的上探、下钻等语义操作.在DHAC中进行数据插入和删除等数据更新时,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.实现了在插入新维或维层次时不需要重新构建聚集Cube就可以实现Cube的模式更新.对维层次聚集Cube与传统Cube进行了算法性能分析和比较,理论分析和实验结果都表明,所提出的DHAC性能最佳.In this paper it is proposed to create high performance DHAC （dimension hierarchy aggregate cube） with the dimension hierarchy aggregate technique on the cube. By using the dimension hierarchy of the dimension hierarchy aggregate tree, the DHAC can optimize the query efficiency and the update efficiency, and the cube semantic operation such as roll up and drill down can also be supported. The DHAC can incrementally update all the affected ancestor notes while updating the data cell by insertion and deletion in it. The DHAC 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. The algorithms of DHAC are compared with all the existing ones such as SDDC（space-efficient dynamic data cube） by more experiment. The analytical and experimental results show that the algorithms of DHAC proposed are more efficient than other existing ones.

关 键 词：数据仓库系统 维层次聚集 CUBE 存储结构 多维联机分析处理 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]