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

15 Citationer (Scopus)


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


Konference2014 IEEE International Conference on Communications
NavnIEEE International Conference on Communications

Fingeraftryk Dyk ned i forskningsemnerne om 'Implementation and Performance Evaluation of Distributed Cloud Storage Solutions using Random Linear Network Coding'. Sammen danner de et unikt fingeraftryk.