Hybrid Regenerating Codes for Distributed Storage Systems

Abstract

Distributed storage systems are mainly justified due to their ability to store data reliably over some unreliable nodes such that the system can have long term durability. Recently, regenerating codes are proposed to make a balance between the repair bandwidth and the storage capacity per node. This is achieved through using the notion of network coding approach. In this paper, a new variation of these codes, called hybrid regenerating codes incorporating a super node is proposed, showing in some cases the new code outperforming existing regenerating codes in terms of the repair bandwidth and/or download cost.