Distributed Online En-Route Caching

Ammar Gharaibeh, Abdallah Khreishah, Issa Khalil, Jie Wu

Research output: Contribution to journalArticle

Abstract

Content caching at intermediate nodes is an effective way to optimize the operations of Computer networks, so that future requests can be served without going back to the origin of the content. Several caching techniques have been proposed in literature, including techniques that require major changes to the Internet architecture. In this work, we present a low complexity, distributed, and online caching algorithm based on content popularity. Our algorithm performs en-route caching using a simple cost-reward comparison. Therefore, it can be integrated with the current TCP/IP model. We use the concept of competitive ratio to measure the performance of any online caching algorithm, in terms of traffic savings, with respect to the performance of the optimal offline algorithm that has a complete knowledge of the future. We show that under our settings, no online algorithm can achieve a better competitive ratio than Ω(log n), where n is the number of nodes in the network. Furthermore, we show that under realistic scenarios, our algorithm has an asymptotically optimal competitive ratio in terms of the number of nodes in the network. We also study several extensions to the basic algorithm and show their effectiveness through extensive simulations.

Original languageEnglish
Article number7442568
Pages (from-to)3455-3468
Number of pages14
JournalIEEE Transactions on Parallel and Distributed Systems
Volume27
Issue number12
DOIs
Publication statusPublished - 1 Dec 2016

Fingerprint

Computer networks
Internet
Costs

Keywords

  • asymptotic optimality
  • caching incentive
  • competitive ratio
  • En-route caching
  • quality of service

ASJC Scopus subject areas

  • Signal Processing
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Distributed Online En-Route Caching. / Gharaibeh, Ammar; Khreishah, Abdallah; Khalil, Issa; Wu, Jie.

In: IEEE Transactions on Parallel and Distributed Systems, Vol. 27, No. 12, 7442568, 01.12.2016, p. 3455-3468.

Research output: Contribution to journalArticle

Gharaibeh, Ammar ; Khreishah, Abdallah ; Khalil, Issa ; Wu, Jie. / Distributed Online En-Route Caching. In: IEEE Transactions on Parallel and Distributed Systems. 2016 ; Vol. 27, No. 12. pp. 3455-3468.
@article{9735d9d9dab34c829c34b499e0f614dc,
title = "Distributed Online En-Route Caching",
abstract = "Content caching at intermediate nodes is an effective way to optimize the operations of Computer networks, so that future requests can be served without going back to the origin of the content. Several caching techniques have been proposed in literature, including techniques that require major changes to the Internet architecture. In this work, we present a low complexity, distributed, and online caching algorithm based on content popularity. Our algorithm performs en-route caching using a simple cost-reward comparison. Therefore, it can be integrated with the current TCP/IP model. We use the concept of competitive ratio to measure the performance of any online caching algorithm, in terms of traffic savings, with respect to the performance of the optimal offline algorithm that has a complete knowledge of the future. We show that under our settings, no online algorithm can achieve a better competitive ratio than Ω(log n), where n is the number of nodes in the network. Furthermore, we show that under realistic scenarios, our algorithm has an asymptotically optimal competitive ratio in terms of the number of nodes in the network. We also study several extensions to the basic algorithm and show their effectiveness through extensive simulations.",
keywords = "asymptotic optimality, caching incentive, competitive ratio, En-route caching, quality of service",
author = "Ammar Gharaibeh and Abdallah Khreishah and Issa Khalil and Jie Wu",
year = "2016",
month = "12",
day = "1",
doi = "10.1109/TPDS.2016.2547396",
language = "English",
volume = "27",
pages = "3455--3468",
journal = "IEEE Transactions on Parallel and Distributed Systems",
issn = "1045-9219",
publisher = "IEEE Computer Society",
number = "12",

}

TY - JOUR

T1 - Distributed Online En-Route Caching

AU - Gharaibeh, Ammar

AU - Khreishah, Abdallah

AU - Khalil, Issa

AU - Wu, Jie

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Content caching at intermediate nodes is an effective way to optimize the operations of Computer networks, so that future requests can be served without going back to the origin of the content. Several caching techniques have been proposed in literature, including techniques that require major changes to the Internet architecture. In this work, we present a low complexity, distributed, and online caching algorithm based on content popularity. Our algorithm performs en-route caching using a simple cost-reward comparison. Therefore, it can be integrated with the current TCP/IP model. We use the concept of competitive ratio to measure the performance of any online caching algorithm, in terms of traffic savings, with respect to the performance of the optimal offline algorithm that has a complete knowledge of the future. We show that under our settings, no online algorithm can achieve a better competitive ratio than Ω(log n), where n is the number of nodes in the network. Furthermore, we show that under realistic scenarios, our algorithm has an asymptotically optimal competitive ratio in terms of the number of nodes in the network. We also study several extensions to the basic algorithm and show their effectiveness through extensive simulations.

AB - Content caching at intermediate nodes is an effective way to optimize the operations of Computer networks, so that future requests can be served without going back to the origin of the content. Several caching techniques have been proposed in literature, including techniques that require major changes to the Internet architecture. In this work, we present a low complexity, distributed, and online caching algorithm based on content popularity. Our algorithm performs en-route caching using a simple cost-reward comparison. Therefore, it can be integrated with the current TCP/IP model. We use the concept of competitive ratio to measure the performance of any online caching algorithm, in terms of traffic savings, with respect to the performance of the optimal offline algorithm that has a complete knowledge of the future. We show that under our settings, no online algorithm can achieve a better competitive ratio than Ω(log n), where n is the number of nodes in the network. Furthermore, we show that under realistic scenarios, our algorithm has an asymptotically optimal competitive ratio in terms of the number of nodes in the network. We also study several extensions to the basic algorithm and show their effectiveness through extensive simulations.

KW - asymptotic optimality

KW - caching incentive

KW - competitive ratio

KW - En-route caching

KW - quality of service

UR - http://www.scopus.com/inward/record.url?scp=84997428728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997428728&partnerID=8YFLogxK

U2 - 10.1109/TPDS.2016.2547396

DO - 10.1109/TPDS.2016.2547396

M3 - Article

AN - SCOPUS:84997428728

VL - 27

SP - 3455

EP - 3468

JO - IEEE Transactions on Parallel and Distributed Systems

JF - IEEE Transactions on Parallel and Distributed Systems

SN - 1045-9219

IS - 12

M1 - 7442568

ER -