Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (22): 1-5.

• 博士论坛 • Previous Articles     Next Articles

Efficiency method of partition and parallel & distributed process on high-dimensional Cube

GONG Zhen-zhi1,HU Kong-fa1,2,DA Qing-li1   

  1. 1.School of Economics & Management,Southeast University,Nanjing 210096,China
    2.Department of Computer Science and Engineering,Yangzhou University,Yangzhou,Jiangsu 225009,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-08-01 Published:2007-08-01
  • Contact: GONG Zhen-zhi

一种有效的高维Cube划分与并行分布式处理方法

龚振志1,胡孔法1,2,达庆利1   

  1. 1.东南大学 经济管理学院,南京 210096
    2.扬州大学 计算机科学与工程学院,江苏 扬州 225009
  • 通讯作者: 龚振志

Abstract: A new method-PHD_Cube(a partition and parallel & distributed process of high-dimensional cube) is proposed.PHD_Cube partitions the high dimensional cube into some low-dimensional shell segment mini-Cubes.The shell segment mini-Cubes and their aggregate Cuboids are dynamically constructed from these shell segment mini-Cubes through the data grid or parallel and distributed processing system.The analytical and experimental results show that the performance of PHD_Cube is predominant.

Key words: OnLine Analytical Processing(OLAP), high dimensional cube, parallel and distributed process

摘要: 提出一种高维Cube的划分和并行分布式处理方法PHD_Cube,将高维Cube分割成若干个低维立方体mini-Cube,利用数据网格技术和并行分布式处理系统等并行处理技术来创建这些分割的分段共享mini-Cube及其聚集Cuboids。实验结果表明,PHD_Cube方法的性能优越。

关键词: 联机分析处理(OLAP), 高维Cube, 并行分布式处理