Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding

Frank H.P. Fitzek, Tamas Toth, Aron Szabados, Morten V. Pedersen, Daniel E. Lucani, Marton Sipos, Hassan Charaf, Muriel Medard
2014 2014 IEEE International Conference on Communications Workshops (ICC)  
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-thefly 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
more » ... 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.
doi:10.1109/iccw.2014.6881204 dblp:conf/icc/FitzekTSPLSCM14 fatcat:yprj7smfobf5ljzs47eoqb7d7m