Paper Info
Title
Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding
Abstract
This paper advocates the use of random linear network coding for storage in distributed clouds in order to reduce storage and traffic costs in dynamic settings, i.e. when adding and removing numerous storage devices/clouds on-the-fly and when the number of reachable clouds is limited. We introduce various network coding approaches that trade-off reliability, storage and traffic costs, and system complexity relying on probabilistic recoding for cloud regeneration. We compare these approaches with other approaches based on data replication and Reed-Solomon codes. A simulator has been developed to carry out a thorough performance evaluation of the various approaches when relying on different system settings, e.g., finite fields, and network/storage conditions, e.g., storage space used per cloud, limited network use, and limited recoding capabilities. In contrast to standard coding approaches, our techniques do not require us to retrieve the full original information in order to store meaningful information. Our numerical results show a high resilience over a large number of regeneration cycles compared to other approaches.
Year
DOI
Venue
2014
10.1109/ICCW.2014.6881204
Communications Workshops
Keywords
DocType
ISSN
reed-solomon codes,cloud computing,network coding,performance evaluation,software reliability,storage management,cloud regeneration,data replication,distributed cloud storage solutions,random linear network coding,system complexity,trade-off reliability,traffic costs
Conference
2164-7038
Citations 
PageRank 
References 
9
0.65
5
Authors
8
Name
Order
Citations
PageRank
Frank H. P. Fitzek1706123.89
tamas toth290.65
aron szabados390.65
Morten Videbæk Pedersen420218.49
Daniel Enrique Lucani521718.06
marton sipos690.65
Hassan Charaf721131.15
Muriel Médard86828599.31