Regrouping metric-space search index for search engine size adaptation

Khalil Al Ruqeishi*, Michal Konečný

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This work contributes to the development of search engines that self-adapt their size in response to fluctuations in workload. Deploying a search engine in an Infrastructure as a Service (IaaS) cloud facilitates allocating or deallocating computational resources to or from the engine. In this paper, we focus on the problem of regrouping the metric-space search index when the number of virtual machines used to run the search engine is modified to reflect changes in workload. We propose an algorithm for incrementally adjusting the index to fit the varying number of virtual machines. We tested its performance using a custom-build prototype search engine deployed in the Amazon EC2 cloud, while calibrating the results to compensate for the performance fluctuations of the platform. Our experiments show that, when compared with computing the index from scratch, the incremental algorithm speeds up the index computation 2–10 times while maintaining a similar search performance.
Original languageEnglish
Title of host publicationSimilarity search and applications
Subtitle of host publication8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings
EditorsGiuseppe Amato, Richard Connor, Fabrizio Falchi, Claudio Gennaro
Place of PublicationChem (CH)
PublisherSpringer
Pages271-282
Number of pages12
ISBN (Electronic)978-3-319-25087-8
ISBN (Print)978-3-319-25086-1
DOIs
Publication statusPublished - 17 Oct 2015
Event8th international conference on Similarity Search and Applications - Glasgow, United Kingdom
Duration: 12 Oct 201514 Oct 2015

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume9371
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference8th international conference on Similarity Search and Applications
Abbreviated titleSISAP 2015
CountryUnited Kingdom
CityGlasgow
Period12/10/1514/10/15

Fingerprint

Search engines
Engines
Experiments
Virtual machine

Bibliographical note

© Springer International Publishing Switzerland

Cite this

Al Ruqeishi, K., & Konečný, M. (2015). Regrouping metric-space search index for search engine size adaptation. In G. Amato, R. Connor, F. Falchi, & C. Gennaro (Eds.), Similarity search and applications: 8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings (pp. 271-282 ). (Lecture notes in computer science; Vol. 9371). Chem (CH): Springer. https://doi.org/10.1007/978-3-319-25087-8_26
Al Ruqeishi, Khalil ; Konečný, Michal. / Regrouping metric-space search index for search engine size adaptation. Similarity search and applications: 8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings. editor / Giuseppe Amato ; Richard Connor ; Fabrizio Falchi ; Claudio Gennaro. Chem (CH) : Springer, 2015. pp. 271-282 (Lecture notes in computer science).
@inproceedings{988b8fb5966345b1a193c2a6350bfb63,
title = "Regrouping metric-space search index for search engine size adaptation",
abstract = "This work contributes to the development of search engines that self-adapt their size in response to fluctuations in workload. Deploying a search engine in an Infrastructure as a Service (IaaS) cloud facilitates allocating or deallocating computational resources to or from the engine. In this paper, we focus on the problem of regrouping the metric-space search index when the number of virtual machines used to run the search engine is modified to reflect changes in workload. We propose an algorithm for incrementally adjusting the index to fit the varying number of virtual machines. We tested its performance using a custom-build prototype search engine deployed in the Amazon EC2 cloud, while calibrating the results to compensate for the performance fluctuations of the platform. Our experiments show that, when compared with computing the index from scratch, the incremental algorithm speeds up the index computation 2–10 times while maintaining a similar search performance.",
author = "{Al Ruqeishi}, Khalil and Michal Konečn{\'y}",
note = "{\circledC} Springer International Publishing Switzerland",
year = "2015",
month = "10",
day = "17",
doi = "10.1007/978-3-319-25087-8_26",
language = "English",
isbn = "978-3-319-25086-1",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "271--282",
editor = "Giuseppe Amato and Richard Connor and Fabrizio Falchi and Claudio Gennaro",
booktitle = "Similarity search and applications",
address = "Germany",

}

Al Ruqeishi, K & Konečný, M 2015, Regrouping metric-space search index for search engine size adaptation. in G Amato, R Connor, F Falchi & C Gennaro (eds), Similarity search and applications: 8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings. Lecture notes in computer science, vol. 9371, Springer, Chem (CH), pp. 271-282 , 8th international conference on Similarity Search and Applications, Glasgow, United Kingdom, 12/10/15. https://doi.org/10.1007/978-3-319-25087-8_26

Regrouping metric-space search index for search engine size adaptation. / Al Ruqeishi, Khalil; Konečný, Michal.

Similarity search and applications: 8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings. ed. / Giuseppe Amato; Richard Connor; Fabrizio Falchi; Claudio Gennaro. Chem (CH) : Springer, 2015. p. 271-282 (Lecture notes in computer science; Vol. 9371).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Regrouping metric-space search index for search engine size adaptation

AU - Al Ruqeishi, Khalil

AU - Konečný, Michal

N1 - © Springer International Publishing Switzerland

PY - 2015/10/17

Y1 - 2015/10/17

N2 - This work contributes to the development of search engines that self-adapt their size in response to fluctuations in workload. Deploying a search engine in an Infrastructure as a Service (IaaS) cloud facilitates allocating or deallocating computational resources to or from the engine. In this paper, we focus on the problem of regrouping the metric-space search index when the number of virtual machines used to run the search engine is modified to reflect changes in workload. We propose an algorithm for incrementally adjusting the index to fit the varying number of virtual machines. We tested its performance using a custom-build prototype search engine deployed in the Amazon EC2 cloud, while calibrating the results to compensate for the performance fluctuations of the platform. Our experiments show that, when compared with computing the index from scratch, the incremental algorithm speeds up the index computation 2–10 times while maintaining a similar search performance.

AB - This work contributes to the development of search engines that self-adapt their size in response to fluctuations in workload. Deploying a search engine in an Infrastructure as a Service (IaaS) cloud facilitates allocating or deallocating computational resources to or from the engine. In this paper, we focus on the problem of regrouping the metric-space search index when the number of virtual machines used to run the search engine is modified to reflect changes in workload. We propose an algorithm for incrementally adjusting the index to fit the varying number of virtual machines. We tested its performance using a custom-build prototype search engine deployed in the Amazon EC2 cloud, while calibrating the results to compensate for the performance fluctuations of the platform. Our experiments show that, when compared with computing the index from scratch, the incremental algorithm speeds up the index computation 2–10 times while maintaining a similar search performance.

UR - http://www.scopus.com/inward/record.url?scp=84951855172&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-25087-8_26

DO - 10.1007/978-3-319-25087-8_26

M3 - Conference contribution

AN - SCOPUS:84951855172

SN - 978-3-319-25086-1

T3 - Lecture notes in computer science

SP - 271

EP - 282

BT - Similarity search and applications

A2 - Amato, Giuseppe

A2 - Connor, Richard

A2 - Falchi, Fabrizio

A2 - Gennaro, Claudio

PB - Springer

CY - Chem (CH)

ER -

Al Ruqeishi K, Konečný M. Regrouping metric-space search index for search engine size adaptation. In Amato G, Connor R, Falchi F, Gennaro C, editors, Similarity search and applications: 8th international conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, proceedings. Chem (CH): Springer. 2015. p. 271-282 . (Lecture notes in computer science). https://doi.org/10.1007/978-3-319-25087-8_26