基于压缩特征编码的混合云冗余数据删除算法

发布时间：2018-05-01 13:00

本文选题：云存储系统 + 混合云　；参考：《科技通报》2015年08期

【摘要】：混合云存储系统的大数据部署和管理过程中,出现大量冗余数据,需要对冗余数据合理删除,获取想要云端的数据,提高系统稳定性。传统的冗余数据删除算法会在分数阶Fourier域出现伪峰峰值,不能有效地对冗余数据进行检测滤波和删除处理,提出一种基于压缩特征码的混合云冗余数据删除算法。预测出不同时间片内混合云的任务执行期望完成时间,对混合云数据冗余主成分进行特征编码,表征为校验信息存储子集对部分冗余数据的块层结构,提高冗余数据删除性能,实现算法改进。仿真结果得出,该算法对云存储系统中冗余数据的检测性能较好,有效避免数据信息流的干扰特征造成的误删和漏删,冗余数据删除准确性高,具有较好的应用价值。
[Abstract]:In the course of big data's deployment and management of hybrid cloud storage system, a large number of redundant data appear. It is necessary to delete the redundant data reasonably, to obtain the data of the desired cloud, and to improve the stability of the system. The traditional redundant data deletion algorithm will appear pseudo peak value in fractional Fourier domain, which can not effectively detect, filter and delete redundant data. A hybrid cloud redundant data deletion algorithm based on compression signature is proposed. The expected completion time of task execution of mixed cloud in different time slices is predicted, and the redundant principal components of mixed cloud data are encoded by feature encoding, which is represented as the block layer structure of the partially redundant data stored in a subset of checkout information storage, and the performance of redundant data deletion is improved. The algorithm is improved. The simulation results show that the algorithm has good detection performance for redundant data in cloud storage system, effectively avoids the error deletion and omission caused by the interference characteristics of data information flow, and has high accuracy of redundant data deletion, and has good application value.
【作者单位】：南京机电职业技术学院;
【分类号】：TP333

【参考文献】