An Improved Hilbert Curve for Parallel Spatial Data Partitioning

A novel Hilbert-curve is introduced for parallel spatial data partitioning, with consideration of the huge-amount property of spatial information and the variable-length characteristic of vector data items. Based on the improved Hilbert curve, the algorithm can be designed to achieve almost-uniform spatial data partitioning among multiple disks in parallel spatial databases. Thus, the phenomenon of data imbalance can be significantly avoided and search and query efficiency can be enhanced.

一条新奇 Hilbert 曲线为划分的平行空间数据被介绍，与空间信息和向量数据项的可变长度的特征的巨大数量的性质的考虑。基于改进 Hilbert 弯曲，算法能被设计空间数据在平行空间数据库在多重磁盘之中划分完成几乎制服。因此，数据不平衡的现象能显著地被避免，搜索和询问效率能被提高。