Energy-performance trade-offs for spatial access methods on memory-resident data

Ning An, Sudhanva Gurumurthi, Anand Sivasubramaniam, Narayanan Vijaykrishnan, Mahmut Kandemir, Mary Jane Irwin

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The proliferation of mobile and pervasive computing devices has brought energy constraints into the limelight. Energy-conscious design is important at all levels of system architecture, and the software has a key role, to play in conserving battery energy on these devices. With the increasing popularity of spatial database applications, and their anticipated deployment on mobile devices (such as road atlases and GPS-based applications), it is critical to examine the energy implications of spatial data storage and access methods for memory resident datasets. While there has been extensive prior research on spatial access methods on resource-rich environments, this is, perhaps, the first study to examine their suitability for resource-constrained environments. Using a detailed cycle-accurate energy estimation framework and four different datasets, this paper examines the pros and cons of three previously proposed spatial indexing alternatives from both the energy and performance angles. Specifically, the Quadtree, Packed R-tree, and Buddy-Tree structures are evaluated and compared with a brute-force approach that does not use an index. The results show that there are both performance and energy trade-offs between the indexing schemes for the different queries. The nature of the query also plays an important role in determining the energy-performance trade-offs. Further, technological trends and architectural enhancements are influencing factors on the relative behavior of the index structures. The work in the query has a bearing on how and where (on a mobile client or/and on a server) it should be performed for performance and energy savings. The results from this study will be beneficial for the design and implementation of embedded spatial databases, accelerating their deployment on numerous mobile devices.

Original languageEnglish (US)
Pages (from-to)179-197
Number of pages19
JournalVLDB Journal
Volume11
Issue number3
DOIs
StatePublished - Nov 1 2002

Fingerprint

Mobile devices
Data storage equipment
Mobile computing
Ubiquitous computing
Global positioning system
Energy conservation
Servers

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Hardware and Architecture

Cite this

@article{5be7ce4b61694ca89d876466fd8468a4,
title = "Energy-performance trade-offs for spatial access methods on memory-resident data",
abstract = "The proliferation of mobile and pervasive computing devices has brought energy constraints into the limelight. Energy-conscious design is important at all levels of system architecture, and the software has a key role, to play in conserving battery energy on these devices. With the increasing popularity of spatial database applications, and their anticipated deployment on mobile devices (such as road atlases and GPS-based applications), it is critical to examine the energy implications of spatial data storage and access methods for memory resident datasets. While there has been extensive prior research on spatial access methods on resource-rich environments, this is, perhaps, the first study to examine their suitability for resource-constrained environments. Using a detailed cycle-accurate energy estimation framework and four different datasets, this paper examines the pros and cons of three previously proposed spatial indexing alternatives from both the energy and performance angles. Specifically, the Quadtree, Packed R-tree, and Buddy-Tree structures are evaluated and compared with a brute-force approach that does not use an index. The results show that there are both performance and energy trade-offs between the indexing schemes for the different queries. The nature of the query also plays an important role in determining the energy-performance trade-offs. Further, technological trends and architectural enhancements are influencing factors on the relative behavior of the index structures. The work in the query has a bearing on how and where (on a mobile client or/and on a server) it should be performed for performance and energy savings. The results from this study will be beneficial for the design and implementation of embedded spatial databases, accelerating their deployment on numerous mobile devices.",
author = "Ning An and Sudhanva Gurumurthi and Anand Sivasubramaniam and Narayanan Vijaykrishnan and Mahmut Kandemir and Irwin, {Mary Jane}",
year = "2002",
month = "11",
day = "1",
doi = "10.1007/s00778-002-0073-x",
language = "English (US)",
volume = "11",
pages = "179--197",
journal = "VLDB Journal",
issn = "1066-8888",
publisher = "Springer New York",
number = "3",

}

Energy-performance trade-offs for spatial access methods on memory-resident data. / An, Ning; Gurumurthi, Sudhanva; Sivasubramaniam, Anand; Vijaykrishnan, Narayanan; Kandemir, Mahmut; Irwin, Mary Jane.

In: VLDB Journal, Vol. 11, No. 3, 01.11.2002, p. 179-197.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Energy-performance trade-offs for spatial access methods on memory-resident data

AU - An, Ning

AU - Gurumurthi, Sudhanva

AU - Sivasubramaniam, Anand

AU - Vijaykrishnan, Narayanan

AU - Kandemir, Mahmut

AU - Irwin, Mary Jane

PY - 2002/11/1

Y1 - 2002/11/1

N2 - The proliferation of mobile and pervasive computing devices has brought energy constraints into the limelight. Energy-conscious design is important at all levels of system architecture, and the software has a key role, to play in conserving battery energy on these devices. With the increasing popularity of spatial database applications, and their anticipated deployment on mobile devices (such as road atlases and GPS-based applications), it is critical to examine the energy implications of spatial data storage and access methods for memory resident datasets. While there has been extensive prior research on spatial access methods on resource-rich environments, this is, perhaps, the first study to examine their suitability for resource-constrained environments. Using a detailed cycle-accurate energy estimation framework and four different datasets, this paper examines the pros and cons of three previously proposed spatial indexing alternatives from both the energy and performance angles. Specifically, the Quadtree, Packed R-tree, and Buddy-Tree structures are evaluated and compared with a brute-force approach that does not use an index. The results show that there are both performance and energy trade-offs between the indexing schemes for the different queries. The nature of the query also plays an important role in determining the energy-performance trade-offs. Further, technological trends and architectural enhancements are influencing factors on the relative behavior of the index structures. The work in the query has a bearing on how and where (on a mobile client or/and on a server) it should be performed for performance and energy savings. The results from this study will be beneficial for the design and implementation of embedded spatial databases, accelerating their deployment on numerous mobile devices.

AB - The proliferation of mobile and pervasive computing devices has brought energy constraints into the limelight. Energy-conscious design is important at all levels of system architecture, and the software has a key role, to play in conserving battery energy on these devices. With the increasing popularity of spatial database applications, and their anticipated deployment on mobile devices (such as road atlases and GPS-based applications), it is critical to examine the energy implications of spatial data storage and access methods for memory resident datasets. While there has been extensive prior research on spatial access methods on resource-rich environments, this is, perhaps, the first study to examine their suitability for resource-constrained environments. Using a detailed cycle-accurate energy estimation framework and four different datasets, this paper examines the pros and cons of three previously proposed spatial indexing alternatives from both the energy and performance angles. Specifically, the Quadtree, Packed R-tree, and Buddy-Tree structures are evaluated and compared with a brute-force approach that does not use an index. The results show that there are both performance and energy trade-offs between the indexing schemes for the different queries. The nature of the query also plays an important role in determining the energy-performance trade-offs. Further, technological trends and architectural enhancements are influencing factors on the relative behavior of the index structures. The work in the query has a bearing on how and where (on a mobile client or/and on a server) it should be performed for performance and energy savings. The results from this study will be beneficial for the design and implementation of embedded spatial databases, accelerating their deployment on numerous mobile devices.

UR - http://www.scopus.com/inward/record.url?scp=0036876664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036876664&partnerID=8YFLogxK

U2 - 10.1007/s00778-002-0073-x

DO - 10.1007/s00778-002-0073-x

M3 - Article

AN - SCOPUS:0036876664

VL - 11

SP - 179

EP - 197

JO - VLDB Journal

JF - VLDB Journal

SN - 1066-8888

IS - 3

ER -