Enabling efficient Reduction and Compression: Design of a user-friendly Big Data Biology Life Cycle

Datum

27.02.2015

Zeit

16:30 - 17:30

Sprecher

Humanshu Bhatia

Sprache

en

Hauptthema

Informatik

Andere Themen

Informatik

Beschreibung

The thesis discusses the problem of transferring data from a producer to the storage resources. The scientists at Max Planck Institute of Molecular Cell Biology and Genetics use electronic microscopes to generate high-definition images. The microscope generates them at very high speed. Consequently, the local secondary storage devices are insufficient to store such high throughput data. In the implemented prototype the data is stored on the Max Planck CBG grid infrastructure. To be precise, the aim of my thesis is to provide a prototype for Big Data Biology Life Cycle. This prototype is designed for the Max Planck scientists so, minimalist approach is used in the user interface making the software more user friendly. In order to optimize the space required for storage the prototype also implements a compression algorithm. The data in consideration is massive so, the prototype tries to exploit the network bandwidth. To handle such huge amount of data various open source tools are available. For the current prototype I have used two systems - iRODS(Data-Management system) and UNICORE(Grid computing technology). The developed GUI interface uses either of them at a point of time. Multiple tests have been carried out to measure the performance. Results of these experiments are then used to discuss the advantages and limitations of the current design. Diese Veranstaltung wird unterstützt von Professur für Rechnerarchitektur.

Letztmalig verändert: 27.02.2015, 08:50:29