Distributed storage systems and connection to network coding

Abstract

Distributed storage systems aim at providing a reliable storage over unreliable nodes thorough introducing redundancy. In these systems when a node is failed to retain the previous reliability a newcomer is connected to existing nodes and downloads the same amount of information as the damage node. Thus, a great deal of data transferring, called the repair bandwidth, is imposed to the system. Recently, regenerating codes are introduced to reduce the repair bandwidth through using the notion of network coding. Furthermore, in [1] the generalized regenerating codes are proposed which is an extension of regenerating codes for the case of having different download cost from surviving nodes. The current paper provides a real world example to explain the main difference between regenerating codes and generalized regenerating codes.