Multidimensional query processing algorithm by dimension transformation.

Autor: Rimi RT; Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh. rejwana@kuet.ac.bd., Hasan KMA; Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh., Tsuji T; Faculty of Engineering, University of Fukui, Fukui-shi, Japan.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2023 Apr 11; Vol. 13 (1), pp. 5903. Date of Electronic Publication: 2023 Apr 11.
DOI: 10.1038/s41598-023-31758-7
Abstrakt: Multidimensional query processing is an important access pattern for multidimensional scientific data. We propose an in-memory multidimensional query processing algorithm for dense data using a higher-dimensional array. We developed a new array system namely a Converted two-dimensional Array (C2A) of a multidimensional array of dimension n ([Formula: see text]) where the n dimensions are transformed into 2 dimensions. Using the C2A, we design and analyze less complex algorithms that show improve performance for data locality and cache miss rate. Therefore, improved performance for data retrieval is achieved. We demonstrate algorithms for single key and range key queries for both Traditional Multidimensional Array(TMA) and C2A. We also compare the performance of both schemes. The cost of index computation gets high when the number of dimensions increases in a TMA but the proposed C2A based algorithm shows less computation cost. The cache miss rate is also lower for in C2A based algorithm than TMA based algorithm. Theoretical and experimental results show that the performance of C2A based algorithm outperforms the TMA-based algorithms.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje