Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding

Frank Fitzek, Tamas Toth, Áron Szabados, Morten Videbæk Pedersen, Daniel Enrique Lucani Roetter, Márton Sipos, Hassan Charaf, Muriel Medard

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

13 Citationer (Scopus)

Resumé

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.
OriginalsprogEngelsk
TitelCommunications Workshops (ICC), 2014 IEEE International Conference on
ForlagIEEE Press
Publikationsdato2014
Sider249-254
ISBN (Trykt)9781479946402
DOI
StatusUdgivet - 2014
Begivenhed2014 IEEE International Conference on Communications - Sydney , Australien
Varighed: 10 jun. 201414 jun. 2014
Konferencens nummer: 31675

Konference

Konference2014 IEEE International Conference on Communications
Nummer31675
LandAustralien
BySydney
Periode10/06/201414/06/2014
NavnIEEE International Conference on Communications
ISSN1938-1883

Fingerprint

Linear networks
Network coding
Reed-Solomon codes
Costs
Simulators

Citer dette

Fitzek, F., Toth, T., Szabados, Á., Pedersen, M. V., Roetter, D. E. L., Sipos, M., ... Medard, M. (2014). Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding. I Communications Workshops (ICC), 2014 IEEE International Conference on (s. 249-254). IEEE Press. IEEE International Conference on Communications https://doi.org/10.1109/ICCW.2014.6881204
Fitzek, Frank ; Toth, Tamas ; Szabados, Áron ; Pedersen, Morten Videbæk ; Roetter, Daniel Enrique Lucani ; Sipos, Márton ; Charaf, Hassan ; Medard, Muriel. / Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding. Communications Workshops (ICC), 2014 IEEE International Conference on. IEEE Press, 2014. s. 249-254 (IEEE International Conference on Communications).
@inproceedings{28f4b3b898fc495280d5b6b5426c2e77,
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.",
author = "Frank Fitzek and Tamas Toth and {\'A}ron Szabados and Pedersen, {Morten Videb{\ae}k} and Roetter, {Daniel Enrique Lucani} and M{\'a}rton Sipos and Hassan Charaf and Muriel Medard",
year = "2014",
doi = "10.1109/ICCW.2014.6881204",
language = "English",
isbn = "9781479946402",
pages = "249--254",
booktitle = "Communications Workshops (ICC), 2014 IEEE International Conference on",
publisher = "IEEE Press",

}

Fitzek, F, Toth, T, Szabados, Á, Pedersen, MV, Roetter, DEL, Sipos, M, Charaf, H & Medard, M 2014, Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding. i Communications Workshops (ICC), 2014 IEEE International Conference on. IEEE Press, IEEE International Conference on Communications, s. 249-254, 2014 IEEE International Conference on Communications, Sydney , Australien, 10/06/2014. https://doi.org/10.1109/ICCW.2014.6881204

Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding. / Fitzek, Frank; Toth, Tamas; Szabados, Áron; Pedersen, Morten Videbæk; Roetter, Daniel Enrique Lucani; Sipos, Márton; Charaf, Hassan; Medard, Muriel.

Communications Workshops (ICC), 2014 IEEE International Conference on. IEEE Press, 2014. s. 249-254 (IEEE International Conference on Communications).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding

AU - Fitzek, Frank

AU - Toth, Tamas

AU - Szabados, Áron

AU - Pedersen, Morten Videbæk

AU - Roetter, Daniel Enrique Lucani

AU - Sipos, Márton

AU - Charaf, Hassan

AU - Medard, Muriel

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

U2 - 10.1109/ICCW.2014.6881204

DO - 10.1109/ICCW.2014.6881204

M3 - Article in proceeding

SN - 9781479946402

SP - 249

EP - 254

BT - Communications Workshops (ICC), 2014 IEEE International Conference on

PB - IEEE Press

ER -

Fitzek F, Toth T, Szabados Á, Pedersen MV, Roetter DEL, Sipos M et al. Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding. I Communications Workshops (ICC), 2014 IEEE International Conference on. IEEE Press. 2014. s. 249-254. (IEEE International Conference on Communications). https://doi.org/10.1109/ICCW.2014.6881204