Abstract: The main weak point of Erasure Code algorithm based on the single server scenario is that the system efficiency is low when lots of users access system. This paper proposed decentralized Erasure Code to solve the problem. Redundant storage was achieved by the partition and encoding of the original data. The experimental results show that this algorithm can ensure data reliability and confidentiality in the Cloud storage environment. It can also avoid the load overweight of the single server and improve the throughput and resource utilization of the system.

Key words: cloud storage, reliability, encode, decode, redundancy degree

摘要： 基于单服务器的Erasure Code算法，在网络中存在大量用户访问系统，容易导致系统效率低的问题。为此，提出一种基于分散式服务器的算法，通过对原数据进行分割编码来实现数据块的冗余存储。实验结果表明，该算法能够确保云存储环境下数据的可靠性与保密性，较好地避免单服务器负载过重，同时提高了系统的吞吐量和资源利用率。

关键词: 云存储, 可靠性, 编码, 解码, 冗余度