XCache: Rethinking edge caching for developing regions

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

Abstract

End-users in emerging markets experience poor web performance due to a combination of three factors: high server response time, limited edge bandwidth and the complexity of web pages. .e absence of cloud infrastructure in developing regions and the limited bandwidth experienced by edge nodes constrain the effectiveness of conventional caching solutions for these contexts. .is paper describes the design, implementation and deployment of xCache, a cloud-managed Internet caching architecture that aims to proactively profile popular web pages and maintain the liveness of popular content at so.ware defined edge caches to enhance the cache hit rate with minimal bandwidth overhead. xCache uses a Cloud Controller that continuously analyzes active cloud-managed web pages and derives an object-group representation of web pages based on the objects of a page. Using this object-group representation, xCache computes a bandwidth-Aware utility measure to derive the most valuable configuration for each edge cache. Our preliminary real-world deployment across university campuses in three developing regions demonstrates its potential compared to conventional caching by improving cache hit rates by about 15%. Our evaluations of xCache have also shown that it can be applied in conjunction with other web optimizations solutions like Shandian, and can improve page load times by more than 50%.

Original languageEnglish (US)
Title of host publicationProceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017
PublisherAssociation for Computing Machinery
VolumePart F132087
ISBN (Electronic)9781450352772
DOIs
StatePublished - Nov 16 2017
Event9th International Conference on Information and Communication Technologies and Development, ICTD 2017 - Lahore, Pakistan
Duration: Nov 16 2017Nov 19 2017

Other

Other9th International Conference on Information and Communication Technologies and Development, ICTD 2017
CountryPakistan
CityLahore
Period11/16/1711/19/17

Fingerprint

Websites
Bandwidth
Response time (computer systems)
Servers
Internet
Controllers

Keywords

  • Cache management
  • Distributed web caching
  • Web performance

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Raza, A., Zaki, Y., Poestch, T., Chen, J., & Subramanian, L. (2017). XCache: Rethinking edge caching for developing regions. In Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017 (Vol. Part F132087). [3136577] Association for Computing Machinery. https://doi.org/10.1145/3136560.3136577

XCache : Rethinking edge caching for developing regions. / Raza, Ali; Zaki, Yasir; Poestch, Thomas; Chen, Jay; Subramanian, Lakshminarayanan.

Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017. Vol. Part F132087 Association for Computing Machinery, 2017. 3136577.

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

Raza, A, Zaki, Y, Poestch, T, Chen, J & Subramanian, L 2017, XCache: Rethinking edge caching for developing regions. in Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017. vol. Part F132087, 3136577, Association for Computing Machinery, 9th International Conference on Information and Communication Technologies and Development, ICTD 2017, Lahore, Pakistan, 11/16/17. https://doi.org/10.1145/3136560.3136577
Raza A, Zaki Y, Poestch T, Chen J, Subramanian L. XCache: Rethinking edge caching for developing regions. In Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017. Vol. Part F132087. Association for Computing Machinery. 2017. 3136577 https://doi.org/10.1145/3136560.3136577
Raza, Ali ; Zaki, Yasir ; Poestch, Thomas ; Chen, Jay ; Subramanian, Lakshminarayanan. / XCache : Rethinking edge caching for developing regions. Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017. Vol. Part F132087 Association for Computing Machinery, 2017.
@inproceedings{2c7e62a1bfa04dda9b47d463aad9b3dd,
title = "XCache: Rethinking edge caching for developing regions",
abstract = "End-users in emerging markets experience poor web performance due to a combination of three factors: high server response time, limited edge bandwidth and the complexity of web pages. .e absence of cloud infrastructure in developing regions and the limited bandwidth experienced by edge nodes constrain the effectiveness of conventional caching solutions for these contexts. .is paper describes the design, implementation and deployment of xCache, a cloud-managed Internet caching architecture that aims to proactively profile popular web pages and maintain the liveness of popular content at so.ware defined edge caches to enhance the cache hit rate with minimal bandwidth overhead. xCache uses a Cloud Controller that continuously analyzes active cloud-managed web pages and derives an object-group representation of web pages based on the objects of a page. Using this object-group representation, xCache computes a bandwidth-Aware utility measure to derive the most valuable configuration for each edge cache. Our preliminary real-world deployment across university campuses in three developing regions demonstrates its potential compared to conventional caching by improving cache hit rates by about 15{\%}. Our evaluations of xCache have also shown that it can be applied in conjunction with other web optimizations solutions like Shandian, and can improve page load times by more than 50{\%}.",
keywords = "Cache management, Distributed web caching, Web performance",
author = "Ali Raza and Yasir Zaki and Thomas Poestch and Jay Chen and Lakshminarayanan Subramanian",
year = "2017",
month = "11",
day = "16",
doi = "10.1145/3136560.3136577",
language = "English (US)",
volume = "Part F132087",
booktitle = "Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - XCache

T2 - Rethinking edge caching for developing regions

AU - Raza, Ali

AU - Zaki, Yasir

AU - Poestch, Thomas

AU - Chen, Jay

AU - Subramanian, Lakshminarayanan

PY - 2017/11/16

Y1 - 2017/11/16

N2 - End-users in emerging markets experience poor web performance due to a combination of three factors: high server response time, limited edge bandwidth and the complexity of web pages. .e absence of cloud infrastructure in developing regions and the limited bandwidth experienced by edge nodes constrain the effectiveness of conventional caching solutions for these contexts. .is paper describes the design, implementation and deployment of xCache, a cloud-managed Internet caching architecture that aims to proactively profile popular web pages and maintain the liveness of popular content at so.ware defined edge caches to enhance the cache hit rate with minimal bandwidth overhead. xCache uses a Cloud Controller that continuously analyzes active cloud-managed web pages and derives an object-group representation of web pages based on the objects of a page. Using this object-group representation, xCache computes a bandwidth-Aware utility measure to derive the most valuable configuration for each edge cache. Our preliminary real-world deployment across university campuses in three developing regions demonstrates its potential compared to conventional caching by improving cache hit rates by about 15%. Our evaluations of xCache have also shown that it can be applied in conjunction with other web optimizations solutions like Shandian, and can improve page load times by more than 50%.

AB - End-users in emerging markets experience poor web performance due to a combination of three factors: high server response time, limited edge bandwidth and the complexity of web pages. .e absence of cloud infrastructure in developing regions and the limited bandwidth experienced by edge nodes constrain the effectiveness of conventional caching solutions for these contexts. .is paper describes the design, implementation and deployment of xCache, a cloud-managed Internet caching architecture that aims to proactively profile popular web pages and maintain the liveness of popular content at so.ware defined edge caches to enhance the cache hit rate with minimal bandwidth overhead. xCache uses a Cloud Controller that continuously analyzes active cloud-managed web pages and derives an object-group representation of web pages based on the objects of a page. Using this object-group representation, xCache computes a bandwidth-Aware utility measure to derive the most valuable configuration for each edge cache. Our preliminary real-world deployment across university campuses in three developing regions demonstrates its potential compared to conventional caching by improving cache hit rates by about 15%. Our evaluations of xCache have also shown that it can be applied in conjunction with other web optimizations solutions like Shandian, and can improve page load times by more than 50%.

KW - Cache management

KW - Distributed web caching

KW - Web performance

UR - http://www.scopus.com/inward/record.url?scp=85038586981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038586981&partnerID=8YFLogxK

U2 - 10.1145/3136560.3136577

DO - 10.1145/3136560.3136577

M3 - Conference contribution

AN - SCOPUS:85038586981

VL - Part F132087

BT - Proceedings of the 9th International Conference on Information and Communication Technologies and Development, ICTD 2017

PB - Association for Computing Machinery

ER -