.png){kind=icon}
.png){kind=icon}
Return
Minimum Repair Bandwidth LDPC Codes for Distributed Storage Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2022.3230263.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In distributed storage systems (DSS), an optimal code design must meet the requirements of efficient local data regeneration in addition to reliable data retention. Recently, low-density parity-check (LDPC) codes have been proposed as a promising candidate that can secure high data rates as well as low repair bandwidth while maintaining low complexity in data reconstruction. The main objective of this study is to optimize the repair bandwidth characteristics of LDPC code families for a DSS application while meeting the data reliability requirements. First, a data access scenario in which nodes contact other available nodes randomly to download data is examined. Later, a minimum-bandwidth protocol is considered in which nodes make their selections based on the degree numbers of check nodes. Through formulating optimization problems for both protocols, a fundamental trade-off between the decoding threshold and the repair bandwidth is established for a given code rate. Finally, conclusions are confirmed by numerical results showing that irregular constructions have a large potential for establishing optimized LDPC code families for DSS applications.
Keywords:
Parity check codes
Maintenance engineering
Bandwidth
Decoding
Protocols
Complexity theory
Reliability engineering
Distributed storage
LDPC
data regeneration
BEC
repair
differential evolution (DE)
Journal
IF:
4.4
Papers:
1.3W
Citations:
2.2W