Research Output
Large join order optimization on parallel shared-nothing database machines using genetic algorithms
  This paper proposes the use of genetic algorithms (GAs) for optimizing the sequence of large joins execution on parallel shared-nothing database architectures. In order to measure the suitability of this method we compare the GA that we have specifically developed for this problem with previously proposed GAs. Experimental results show that our GA was able to outperform its counterparts. We also compare the performance of our GA with some known heuristics that were employed for optimizing joins in parallel queries. It turned out that for smaller number of relations, heuristics were able to produce query execution plans as good as those of GAs. However when the number of relations increases, GAs outperform heuristics.

  • Date:

    31 December 1997

  • Publication Status:

    Published

  • Publisher

    Springer Berlin Heidelberg

  • DOI:

    10.1007/bfb0002867

  • ISSN:

    0302-9743

  • Library of Congress:

    QA75 Electronic computers. Computer science

  • Dewey Decimal Classification:

    004 Data processing & computer science

  • Funders:

    Edinburgh Napier Funded

Citation

Nafjan, K. A., & Kerridge, J. M. (1997). Large join order optimization on parallel shared-nothing database machines using genetic algorithms. In Euro-Par'97 Parallel Processing: Third International Euro-Par Conference Passau, Germany, August 26–29, 1997 Proceedings. , (1159-1163). https://doi.org/10.1007/bfb0002867

Authors

Keywords

genetic algorithms; parallel queries; heuristics; shared-nothing

Monthly Views:

Available Documents