@inproceedings{e55dcde2348d4e6293ea8264ba6e9517,
title = "A deduplication algorithm based on data similarity and delta encoding",
abstract = "Satellite applications such as remote sensing application are overwhelmed with vast quantities of data. Nevertheless, the storage resources in the satellite are so limited that it should be used more efficient. The similarity between the remote sensing data is high, but the dissimilar parts of the data distribute irregularly. When using the traditional deduplication algorithm to split the file into chunks, a large amount of chunks are exactly similar but not the same, which results in the bad effect of data deduplication. We propose a deduplication algorithm based on data similarity and delta encoding to reduce the usage of storage resources. The data similarity analysis can find out the similar data. The delta encoding technology can reduce the usage of storage resources. Through experiments on remote sensing application data, we have achieved deduplication ratios up to 30:1, and analyzed how the chunksize affect the experiment results.",
keywords = "Deduplication, Delta encoding, Satellite, Similarity",
author = "Bin Song and Limin Xiao and Guangjun Qin and Li Ruan and Shida Qiu",
note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2017.; 4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016 ; Conference date: 18-11-2016 Through 20-11-2016",
year = "2017",
doi = "10.1007/978-981-10-3969-0\_28",
language = "英语",
isbn = "9789811039683",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "245--253",
editor = "Hanning Yuan and Jing Geng and Fuling Bian",
booktitle = "Geo-Spatial Knowledge and Intelligence - 4th International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2016, Revised Selected Papers",
address = "德国",
}