LDPC Kodlarında Artık Veri Kullanımı Residual Data Usage in LDPC Codes.

Signal Processing and Communications Applications Conference (SIU)(2022)

引用 0|浏览1
暂无评分
摘要
In distributed storage systems/coded caching systems, padding operations should be performed when the encoded data cannot be divided by the number of storage nodes evenly. Thus, extra zero values are stored in one of the nodes to balance each node’s storage content. In this study, distribution of data to storage nodes with no padding was investigated for distributed caching context in which a base station and devices both store the coded data. In other words, no redundancy (no-padding) is included into the encoded data. This approach is named as residual data distribution. LDPC codes are selected as the erasure code due to their low complexity encode/decode operations. Moreover, performance comparisons were conducted between using traditional data distribution approach (with padding) and using residual data (use of no-padding) (standard) in terms of repair time. In our work, the effect of no-padding data usage on the repair time and the ratios of storage savings have been also demonstrated.
更多
查看译文
关键词
ldpc codes,data
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要