Efficient Parallel Processing for K-Nearest-Neighbor Search in Spatial Databases

  • Yunjun Gao
  • Ling Chen
  • Gencai Chen
  • Chun Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3984)


Even though the problem of k nearest neighbor (kNN) query is well-studied in serial environment, there is little prior work on parallel kNN search processing in parallel one. In this paper, we present the first Best-First based Parallel kNN (BFPkNN) query algorithm in a multi-disk setting, for efficient handling of kNN retrieval with arbitrary values of k by parallelization. The core of our method is to access more entries from multiple disks simultaneously and enable several effective pruning heuristics to discard non-qualifying entries. Extensive experiments with real and synthetic datasets confirm that BFPkNN significantly outperforms its competitors in both efficiency and scalability.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Henrich, A.: A distance-scan algorithm for spatial access structures. In: ACM GIS, pp. 136–143 (1994)Google Scholar
  2. 2.
    Roussopoulos, N., Kelley, S., Vincent, F.: Nearest neighbor queries. In: SIGMOD, pp. 71–79 (1995)Google Scholar
  3. 3.
    Cheung, K.L., Fu, A.W.-C.: Enhanced nearest neighbour search on the R-tree. ACM SIGMOD Record 27, 16–21 (1998)CrossRefGoogle Scholar
  4. 4.
    Hjaltason, G.R., Samet, H.: Distance browsing in spatial databases. ACM TODS 24, 265–318 (1999)CrossRefGoogle Scholar
  5. 5.
    Papadopoulos, A.N., Manolopoulos, Y.: Similarity query processing using disk arrays. In: SIGMOD, pp. 225–236 (1998)Google Scholar
  6. 6.
    Guttman, A.: R-trees: a dynamic index structure for spatial searching. In: SIGMOD, pp. 47–57 (1984)Google Scholar
  7. 7.
    Sellis, T., Roussopoulos, N., Faloutsos, C.: The R  + -tree: a dynamic index for multi-dimensional Objects. In: VLDB, pp. 507–518 (1987)Google Scholar
  8. 8.
    Beckmann, N., Kriegel, H.-P., Schneider, R., Seeger, B.: The R*-tree: an efficient and robust access method for points and rectangles. In: SIGMOD, pp. 322–331 (1990)Google Scholar
  9. 9.
    Kamel, I., Faloutsos, C.: Parallel R-trees. In: SIGMOD, pp. 195–204 (1992)Google Scholar
  10. 10.
    Theodoridis, Y., Sellis, T.K.: A model for the prediction of R-tree performance. In: PODS, pp. 161–171 (1996)Google Scholar
  11. 11.
    Berchtold, S., Böhm, C., Braunmüller, B., Keim, D.A., Kriegel, H.-P.: Fast parallel similarity search in multimedia databases. In: SIGMOD, pp. 1–12 (1997)Google Scholar
  12. 12.
    Papadopoulos, A., Manolopoulos, Y.: Parallel processing of nearest neighbor queries in declustered spatial data. In: ACM GIS, pp. 35–43 (1996)Google Scholar
  13. 13.
    Koudas, N., Faloutsos, C., Kamel, I.: Declustering spatial databases on a multi-computer architecture. In: EDBT, pp. 592–614 (1996)Google Scholar
  14. 14.
    Gavrilova, M.L.: On a nearest-neighbor problem under minkowski and power metrics for large data sets. J. of Supercomputing 22, 87–98 (2002)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yunjun Gao
    • 1
  • Ling Chen
    • 1
  • Gencai Chen
    • 1
  • Chun Chen
    • 1
  1. 1.College of Computer ScienceZhejiang UniversityHangzhouP.R. China

Personalised recommendations