Abstract In today’s world, there is plenty of data being generated from various sources in different areas across economics, engineering and science. For instance, accelerators are able to generate 3 PB data just in one experiment. Synchrotrons industry is an example of the volume and velocity of data which data is too big to be analyzed at once. While some light sources can deal with 11 PB, they confront with data problems. The explosion of data become an important and serious issue in today’s synchrotrons world. Totally, these data problems pose in different fields like storage, analytics, visualisation, monitoring and controlling. To override these problems, they prefer HDF5, grid computing, cloud computing and Hadoop/Hbase and NoSQL.Recently, big data takes a lot of attention from academic and industry places. We are looking for an appropriate and feasible solution for data issues in ILSF basically. Contemplating on Hadoop and other up-to-date tools and components is not out of mind as a stable solution. In this Thesis, we are evaluating big data tools and tested techniques in various light source around the world for data in beamlines studying the storage and analytics aspects.In this regard, an online interview has been designed and sent to a number of beamline scientists. The result, contrary to the assumption, is that scientists are more likely to be faced with data transfer, data storage, data processing, and data analysis and analysis with highvolume or high-speed data issues, respectively. Given the data collected about the big data, and in which areas there are more tendencies to use or have already been used these tools, respectively, access to data analysis, data processing, data analysis, storage and data control.
http://disl.ir/wp-content/uploads/2016/07/synchrotron3D.png 574 836 آزمایشگاه علوم داده http://disl.ir/wp-content/uploads/2019/05/DISL-3-300x120.png آزمایشگاه علوم داده2016-07-15 13:46:122019-10-19 13:58:28کاربرد کلان داده در سنکروترون