A Novel Technique for Storage in Cloud Data Centers

Abstract

An Information Dispersal Algorithm takes a file F as a input and divide this file into n pieces that needs to be dispersed among n nodes such that any m pieces out of total n pieces will be sufficient to reconstruct the whole file F. The size of each piece is |F| / m. It must also ensure that the complete knowledge of any m-1 pieces is insufficient to reconstruct the complete file F. The ideas for accomplishing this have been given in many literatures in the past. This manuscript discusses the application of Information Dispersal Algorithms in Storage of files on cloud Data Centers instead of using previous schemes of replication.