Distributed asteroid discovery system for large astronomical data

Chi Sheng Huang, Meng Feng Tsai, Po Hsuan Huang, Li Ding Su, Kuei Sheng Lee

研究成果: 雜誌貢獻期刊論文同行評審

5 引文 斯高帕斯(Scopus)

摘要

Thanks to the advanced technology in astronomical observations, astronomers have collected massive data sets. One of the research tasks is to discover asteroids based on observational data. However, with the fast-growing volume of astronomical data sets, this task becomes enormously relied on computing power. Therefore, the cloud-enable distributed computation and super powerful computation power can offer a good solution to this field. We adopt the Hough transform to link the sequential DETECTIONs of asteroids, and also design a distributed algorithm to process this task on distributed cloud environment for flexible and efficient calculation. Our designs are developed on MapReduce and Spark frameworks. We also utilizes HDFS and HBase in order to reduce disk I/O overhead and increase reliability and scalability. The system architecture is built on the OpenStack which allocates hardware resources flexibly. Our experiment results show significant improvements of calculation time. We believe this will help astronomers to interactively access and analyze data to discover asteroids. The system can also incrementally update DETECTIONs linking with new observed data. It also provides the visual interface to inspect the linked DETECTIONs of asteroids.

原文???core.languages.en_GB???
頁(從 - 到)27-37
頁數11
期刊Journal of Network and Computer Applications
93
DOIs
出版狀態已出版 - 1 9月 2017

指紋

深入研究「Distributed asteroid discovery system for large astronomical data」主題。共同形成了獨特的指紋。

引用此