Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/32164
Title: Peer-to-peer cooperative caching in mobile environments
Authors: Chow, CY
Leong, HV 
Chan, A 
Keywords: Cache storage
Client-server systems
Mobile computing
Performance evaluation
Replicated databases
Issue Date: 2004
Publisher: IEEE
Source: 24th International Conference on Distributed Computing Systems Workshops, 2004 : proceedings : 23-24 March 2004, p. 528-533 How to cite?
Abstract: Caching is a key technique for improving the data retrieval performance of mobile clients in mobile environments. The emergence of robust and reliable peer-to-peer (P2P) technologies now brings to reality what we call "cooperative caching " in which mobile clients can access data items from the cache in their neighboring peers. We discuss cooperative caching in mobile environments and proposes a cooperative caching scheme for mobile systems, called COCA. In COCA, we identify two types of mobile clients: low activity and high activity. They are referred to as low activity mobile client/host (LAM) and high activity mobile client/host (HAM) respectively. Both LAM and HAM can share their cache. The server replicates appropriate data items to LAMs so that HAMs can take advantages of the LAM replicas. The performance of pure COCA and COCA with the data replication scheme is evaluated through a number of simulated experiments which show that COCA significantly reduces both the server workload in terms of number of requests and the access miss ratio when the MHs reside outside of the service area. The COCA with the data replication scheme can improve the overall system performance in other aspects as well.
URI: http://hdl.handle.net/10397/32164
ISBN: 0-7695-2087-1
DOI: 10.1109/ICDCSW.2004.1284083
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

32
Last Week
1
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.