A workload assignment strategy for efficient ROLAP data cube computation in distributed systems

Ilhyun Suh, Yon Dohn Chung

Research output: Contribution to journalArticle

Abstract

Data cube plays a key role in the analysis of multidimensional data. Nowadays, the explosive growth of multidimensional data has made distributed solutions important for data cube computation. Among the architectures for distributed processing, the shared-nothing architecture is known to have the best scalability. However, frequent and massive network communication among the processors can be a performance bottleneck in shared-nothing distributed processing. Therefore, suppressing the amount of data transmission among the processors can be an effective strategy for improving overall performance. In addition, dividing the workload and distributing them evenly to the processors is important. In this paper, the authors present a distributed algorithm for data cube computation that can be adopted in shared-nothing systems. The proposed algorithm gains efficiency by adopting the workload assignment strategy that reduces the total network cost and allocates the workload evenly to each processor, simultaneously.

Original languageEnglish
Pages (from-to)51-71
Number of pages21
JournalInternational Journal of Data Warehousing and Mining
Volume12
Issue number3
DOIs
Publication statusPublished - 2016 Jul 1

Fingerprint

Processing
Parallel algorithms
Data communication systems
Telecommunication networks
Scalability
Costs

Keywords

  • Data Cube
  • Data Warehouse
  • Distributed Processing
  • OLAP
  • ROLAP
  • Shared-Nothing Architecture

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture

Cite this

A workload assignment strategy for efficient ROLAP data cube computation in distributed systems. / Suh, Ilhyun; Chung, Yon Dohn.

In: International Journal of Data Warehousing and Mining, Vol. 12, No. 3, 01.07.2016, p. 51-71.

Research output: Contribution to journalArticle

@article{2f765b3441564aefa567e49a1e357e74,
title = "A workload assignment strategy for efficient ROLAP data cube computation in distributed systems",
abstract = "Data cube plays a key role in the analysis of multidimensional data. Nowadays, the explosive growth of multidimensional data has made distributed solutions important for data cube computation. Among the architectures for distributed processing, the shared-nothing architecture is known to have the best scalability. However, frequent and massive network communication among the processors can be a performance bottleneck in shared-nothing distributed processing. Therefore, suppressing the amount of data transmission among the processors can be an effective strategy for improving overall performance. In addition, dividing the workload and distributing them evenly to the processors is important. In this paper, the authors present a distributed algorithm for data cube computation that can be adopted in shared-nothing systems. The proposed algorithm gains efficiency by adopting the workload assignment strategy that reduces the total network cost and allocates the workload evenly to each processor, simultaneously.",
keywords = "Data Cube, Data Warehouse, Distributed Processing, OLAP, ROLAP, Shared-Nothing Architecture",
author = "Ilhyun Suh and Chung, {Yon Dohn}",
year = "2016",
month = "7",
day = "1",
doi = "10.4018/IJDWM.2016070104",
language = "English",
volume = "12",
pages = "51--71",
journal = "International Journal of Data Warehousing and Mining",
issn = "1548-3924",
publisher = "IGI Publishing",
number = "3",

}

TY - JOUR

T1 - A workload assignment strategy for efficient ROLAP data cube computation in distributed systems

AU - Suh, Ilhyun

AU - Chung, Yon Dohn

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Data cube plays a key role in the analysis of multidimensional data. Nowadays, the explosive growth of multidimensional data has made distributed solutions important for data cube computation. Among the architectures for distributed processing, the shared-nothing architecture is known to have the best scalability. However, frequent and massive network communication among the processors can be a performance bottleneck in shared-nothing distributed processing. Therefore, suppressing the amount of data transmission among the processors can be an effective strategy for improving overall performance. In addition, dividing the workload and distributing them evenly to the processors is important. In this paper, the authors present a distributed algorithm for data cube computation that can be adopted in shared-nothing systems. The proposed algorithm gains efficiency by adopting the workload assignment strategy that reduces the total network cost and allocates the workload evenly to each processor, simultaneously.

AB - Data cube plays a key role in the analysis of multidimensional data. Nowadays, the explosive growth of multidimensional data has made distributed solutions important for data cube computation. Among the architectures for distributed processing, the shared-nothing architecture is known to have the best scalability. However, frequent and massive network communication among the processors can be a performance bottleneck in shared-nothing distributed processing. Therefore, suppressing the amount of data transmission among the processors can be an effective strategy for improving overall performance. In addition, dividing the workload and distributing them evenly to the processors is important. In this paper, the authors present a distributed algorithm for data cube computation that can be adopted in shared-nothing systems. The proposed algorithm gains efficiency by adopting the workload assignment strategy that reduces the total network cost and allocates the workload evenly to each processor, simultaneously.

KW - Data Cube

KW - Data Warehouse

KW - Distributed Processing

KW - OLAP

KW - ROLAP

KW - Shared-Nothing Architecture

UR - http://www.scopus.com/inward/record.url?scp=84991687218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991687218&partnerID=8YFLogxK

U2 - 10.4018/IJDWM.2016070104

DO - 10.4018/IJDWM.2016070104

M3 - Article

AN - SCOPUS:84991687218

VL - 12

SP - 51

EP - 71

JO - International Journal of Data Warehousing and Mining

JF - International Journal of Data Warehousing and Mining

SN - 1548-3924

IS - 3

ER -