Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding
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 v...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2016
|
| Online Access: | http://hdl.handle.net/1721.1/100941 https://orcid.org/0000-0003-4059-407X |
| _version_ | 1826208714577674240 |
|---|---|
| author | Toth, Tamas Szabados, Aron Pedersen, Morten V. Lucani, Daniel Enrique Sipos, Marton Charaf, Hassan Medard, Muriel Fitzek, Frank H. P. |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Toth, Tamas Szabados, Aron Pedersen, Morten V. Lucani, Daniel Enrique Sipos, Marton Charaf, Hassan Medard, Muriel Fitzek, Frank H. P. |
| author_sort | Toth, Tamas |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T14:10:19Z |
| format | Article |
| id | mit-1721.1/100941 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:10:19Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1009412022-10-01T19:37:22Z Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding Toth, Tamas Szabados, Aron Pedersen, Morten V. Lucani, Daniel Enrique Sipos, Marton Charaf, Hassan Medard, Muriel Fitzek, Frank H. P. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Research Laboratory of Electronics Medard, Muriel 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. Danish Council for Independent Research (Green Mobile Cloud Project DFF-090201372B) Hungarian National Development Agency (Research and Technology Innovation Fund Grant KMR_12-1-2012-0441) European Union (European Social Fund Project FuturICT.hu Grant TAMOP- 4.2.2.C-11/1/KONV-2012-0013) 2016-01-20T02:26:52Z 2016-01-20T02:26:52Z 2014-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-4640-2 http://hdl.handle.net/1721.1/100941 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). https://orcid.org/0000-0003-4059-407X en_US http://dx.doi.org/10.1109/ICCW.2014.6881204 Proceedings of the 2014 IEEE International Conference on Communications Workshops (ICC) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Toth, Tamas Szabados, Aron Pedersen, Morten V. Lucani, Daniel Enrique Sipos, Marton Charaf, Hassan Medard, Muriel Fitzek, Frank H. P. Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title | Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title_full | Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title_fullStr | Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title_full_unstemmed | Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title_short | Implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| title_sort | implementation and performance evaluation of distributed cloud storage solutions using random linear network coding |
| url | http://hdl.handle.net/1721.1/100941 https://orcid.org/0000-0003-4059-407X |
| work_keys_str_mv | AT tothtamas implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT szabadosaron implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT pedersenmortenv implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT lucanidanielenrique implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT siposmarton implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT charafhassan implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT medardmuriel implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding AT fitzekfrankhp implementationandperformanceevaluationofdistributedcloudstoragesolutionsusingrandomlinearnetworkcoding |