Home > Research > Publications & Outputs > A Distributed Caching Approach for Improved Dat...

Electronic data

  • CSCI4584

    633 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

A Distributed Caching Approach for Improved Data Availability in Rural Wireless Mesh Networks

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Publication date16/12/2016
Host publication Computational Science and Computational Intelligence (CSCI), 2016 International Conference on
Place of Publication16772962
PublisherIEEE
Pages904 - 910
Number of pages7
ISBN (electronic)9781509055104
ISBN (print)9781509055111
<mark>Original language</mark>English
EventInternational Conference on Computational Science and Computational Intelligence - Monte Carlo Hotel, Las Vegas, United States
Duration: 15/12/201617/12/2016

Conference

ConferenceInternational Conference on Computational Science and Computational Intelligence
Abbreviated title (CSCI)
Country/TerritoryUnited States
CityLas Vegas
Period15/12/1617/12/16

Conference

ConferenceInternational Conference on Computational Science and Computational Intelligence
Abbreviated title (CSCI)
Country/TerritoryUnited States
CityLas Vegas
Period15/12/1617/12/16

Abstract

The performance of wireless mesh networks (WMNs) deployed for Internet access in rural settings is affected by several factors. Typically, deployments in African domains use cheap and computationally constrained devices with challenges such as power fluctuations, gateway congestion, VSAT communications asymmetry and low bandwidth, which affects throughput under dynamic scenarios. Caching methods can offer improvement for content availability to ensure a reliable quality of experience (QoE) for rural dwellers. Primarily, we integrate a modified multicast technique and overhearing for object caching and cache dissemination. We proposed a Distributed Overheard-object Caching Approach (DOCA) and evaluated the performance employing simulations. The outcome shows significant improvements over the random-path-cache-request (RPCR) strategy with increased data availability and reduced communication cost regarding response time for the outlined rural scenarios. Moreover, the optimization of gateway load helps to conserve network resources such as bandwidth and nodal energy considerably.