The power of prediction: Cloud bandwidth and cost reduction

Eyal Zohar; Israel Cidon; Osnat Ossi Mokryn

doi:10.1145/2043164.2018447

The power of prediction: Cloud bandwidth and cost reduction

Eyal Zohar, Israel Cidon, Osnat Ossi Mokryn

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper we present PACK (Predictive ACKs), a novel end-to-end Traffic Redundancy Elimination (TRE) system, designed for cloud computing customers. Cloud-based TRE needs to apply a judicious use of cloud resources so that the bandwidth cost reduction combined with the additional cost of TRE computation and storage would be optimized. PACK's main advantage is its capability of offloading the cloud-server TRE effort to end-clients, thus minimizing the processing costs induced by the TRE algorithm. Unlike previous solutions, PACK does not require the server to continuously maintain clients' status. This makes PACK very suitable for pervasive computation environments that combine client mobility and server migration to maintain cloud elasticity. PACK is based on a novel TRE technique, which allows the client to use newly received chunks to identify previously received chunk chains, which in turn can be used as reliable predictors to future transmitted chunks. We present a fully functional PACK implementation, transparent to all TCP-based applications and network devices. Finally, we analyze PACK benefits for cloud users, using traffic traces from various sources.

Original language	English
Pages (from-to)	86-97
Number of pages	12
Journal	Computer Communication Review
Volume	41
Issue number	4
DOIs	https://doi.org/10.1145/2043164.2018447
State	Published - 15 Aug 2011
Externally published	Yes

Bibliographical note

Funding Information:
This work is partially supported by the VENUS-C project, co-funded within the 7th Framework Programme by the GÉANT & e-Infrastructure Unit, Information Society & Media Directorate General of the European Commission, Contract 261565. It is also partially supported by NET-HD MAGNET program of the office of the Chief Scientist of the Israeli Ministry of Industry, Trade, and Labor. We would like to thank our partners in Venus-C and NET-HD projects for their invaluable feedback and insight.

Publisher Copyright:
© 2011 ACM.

Keywords

Caching
Cloud computing
Network optimization
Traffic redundancy elimination

ASJC Scopus subject areas

Software
Computer Networks and Communications

Access to Document

10.1145/2043164.2018447

Cite this

@article{c12a61c0766347889dfe719faf66c3ae,

title = "The power of prediction: Cloud bandwidth and cost reduction",

abstract = "In this paper we present PACK (Predictive ACKs), a novel end-to-end Traffic Redundancy Elimination (TRE) system, designed for cloud computing customers. Cloud-based TRE needs to apply a judicious use of cloud resources so that the bandwidth cost reduction combined with the additional cost of TRE computation and storage would be optimized. PACK's main advantage is its capability of offloading the cloud-server TRE effort to end-clients, thus minimizing the processing costs induced by the TRE algorithm. Unlike previous solutions, PACK does not require the server to continuously maintain clients' status. This makes PACK very suitable for pervasive computation environments that combine client mobility and server migration to maintain cloud elasticity. PACK is based on a novel TRE technique, which allows the client to use newly received chunks to identify previously received chunk chains, which in turn can be used as reliable predictors to future transmitted chunks. We present a fully functional PACK implementation, transparent to all TCP-based applications and network devices. Finally, we analyze PACK benefits for cloud users, using traffic traces from various sources.",

keywords = "Caching, Cloud computing, Network optimization, Traffic redundancy elimination",

author = "Eyal Zohar and Israel Cidon and Mokryn, {Osnat Ossi}",

note = "Funding Information: This work is partially supported by the VENUS-C project, co-funded within the 7th Framework Programme by the G{\'E}ANT & e-Infrastructure Unit, Information Society & Media Directorate General of the European Commission, Contract 261565. It is also partially supported by NET-HD MAGNET program of the office of the Chief Scientist of the Israeli Ministry of Industry, Trade, and Labor. We would like to thank our partners in Venus-C and NET-HD projects for their invaluable feedback and insight. Publisher Copyright: {\textcopyright} 2011 ACM.",

year = "2011",

month = aug,

day = "15",

doi = "10.1145/2043164.2018447",

language = "English",

volume = "41",

pages = "86--97",

journal = "Computer Communication Review",

issn = "0146-4833",

publisher = "Association for Computing Machinery (ACM)",

number = "4",

}

TY - JOUR

T1 - The power of prediction

T2 - Cloud bandwidth and cost reduction

AU - Zohar, Eyal

AU - Cidon, Israel

AU - Mokryn, Osnat Ossi

N1 - Funding Information: This work is partially supported by the VENUS-C project, co-funded within the 7th Framework Programme by the GÉANT & e-Infrastructure Unit, Information Society & Media Directorate General of the European Commission, Contract 261565. It is also partially supported by NET-HD MAGNET program of the office of the Chief Scientist of the Israeli Ministry of Industry, Trade, and Labor. We would like to thank our partners in Venus-C and NET-HD projects for their invaluable feedback and insight. Publisher Copyright: © 2011 ACM.

PY - 2011/8/15

Y1 - 2011/8/15

N2 - In this paper we present PACK (Predictive ACKs), a novel end-to-end Traffic Redundancy Elimination (TRE) system, designed for cloud computing customers. Cloud-based TRE needs to apply a judicious use of cloud resources so that the bandwidth cost reduction combined with the additional cost of TRE computation and storage would be optimized. PACK's main advantage is its capability of offloading the cloud-server TRE effort to end-clients, thus minimizing the processing costs induced by the TRE algorithm. Unlike previous solutions, PACK does not require the server to continuously maintain clients' status. This makes PACK very suitable for pervasive computation environments that combine client mobility and server migration to maintain cloud elasticity. PACK is based on a novel TRE technique, which allows the client to use newly received chunks to identify previously received chunk chains, which in turn can be used as reliable predictors to future transmitted chunks. We present a fully functional PACK implementation, transparent to all TCP-based applications and network devices. Finally, we analyze PACK benefits for cloud users, using traffic traces from various sources.

AB - In this paper we present PACK (Predictive ACKs), a novel end-to-end Traffic Redundancy Elimination (TRE) system, designed for cloud computing customers. Cloud-based TRE needs to apply a judicious use of cloud resources so that the bandwidth cost reduction combined with the additional cost of TRE computation and storage would be optimized. PACK's main advantage is its capability of offloading the cloud-server TRE effort to end-clients, thus minimizing the processing costs induced by the TRE algorithm. Unlike previous solutions, PACK does not require the server to continuously maintain clients' status. This makes PACK very suitable for pervasive computation environments that combine client mobility and server migration to maintain cloud elasticity. PACK is based on a novel TRE technique, which allows the client to use newly received chunks to identify previously received chunk chains, which in turn can be used as reliable predictors to future transmitted chunks. We present a fully functional PACK implementation, transparent to all TCP-based applications and network devices. Finally, we analyze PACK benefits for cloud users, using traffic traces from various sources.

KW - Caching

KW - Cloud computing

KW - Network optimization

KW - Traffic redundancy elimination

UR - http://www.scopus.com/inward/record.url?scp=85091020118&partnerID=8YFLogxK

U2 - 10.1145/2043164.2018447

DO - 10.1145/2043164.2018447

M3 - Article

AN - SCOPUS:85091020118

SN - 0146-4833

VL - 41

SP - 86

EP - 97

JO - Computer Communication Review

JF - Computer Communication Review

IS - 4

ER -

The power of prediction: Cloud bandwidth and cost reduction

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this