THIS IS THE ARCHIVED SSRC SITE.
Maintained by Ethan L. Miller.
The current CRSS site is at https://www.crss.us/.

Towards Universal Mobile Caching

Appeared in Proceedings of the 4th ACM International Workshop on Data Engineering for Wireless and Mobile Access (MobiDE 2005) (held in conjunction with the ACM SIGMOD 2005).

Abstract

In the context of mobile data access, data caching is fundamental for both performance and functionality. For this reason there have been many studies into developing energy-efficient caching algorithms suitable for specific mobile environments. In this papers, we present a novel caching policy, Universal Mobile Caching (UMC), which is suitable for managing object caches in structurally vary- ing environments, and which is self-optimizing for changing workloads. UMC is based on a simple set of basic criteria which reflect a spectrum of possible caching policies. UMC has demonstrated the ability to provide caching benefits in the on-demand retrieval of web documents for the mobile web, wherein multiple levels of intervening caches can create adverse workloads for other general caching schemes. When considering the energy expended in servicing cache misses, UMC consistently demonstrated savings on the order of 10% to 15%. These energy savings are solely due to local per-node behavior, and do not include the potential reduction of power consumption, to less than half its normal levels, achievable due its enabling more effective multi-hop data transmission.

Publication date:
June 2005

Authors:
Ganesh Santhanakrishnan
Ahmed Amer
Panos Chrysanthis

Projects:
Adaptive Caching

Available media

Full paper text: PDF

Bibtex entry

@inproceedings{amer-mobide05,
  author       = {Ganesh Santhanakrishnan and Ahmed Amer and Panos Chrysanthis},
  title        = {Towards Universal Mobile Caching},
  booktitle    = {Proceedings of the 4th ACM International Workshop on Data Engineering for Wireless and Mobile Access (MobiDE 2005) (held in conjunction with the ACM SIGMOD 2005)},
  month        = jun,
  year         = {2005},
}
Last modified 6 Jun 2019