Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding
Name
Implementation-and-Performance.pdf
Size
465.28 KB
Format
Adobe PDF
Checksum (MD5)
471cd08dd0ca49efd1042bcb1e44b711
Author(s)
Toth, Tamas
Szabados, Aron
Pedersen, Morten V.
Lucani, Daniel Enrique
Sipos, Marton
Charaf, Hassan
Medard, Muriel
Fitzek, Frank H. P.
Date Issued
June 2014
Journal
Proceedings of the 2014 IEEE International Conference on Communications Workshops (ICC)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Fitzek, Frank H.P., Tamas Toth, Aron Szabados, Morten V. Pedersen, Daniel E. Lucani, Marton Sipos, Hassan Charaf, and Muriel Medard. “Implementation and Performance Evaluation of Distributed Cloud Storage Solutions Using Random Linear Network Coding.” 2014 IEEE International Conference on Communications Workshops (ICC) (June 2014).
Version
Author's final manuscript
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Research Laboratory of Electronics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICCW.2014.6881204
