CERN-openlab Workshop on Data Analytics: Technical Session

Wednesday 20 Nov 2013, 14:00 → 17:00 Europe/Zurich

31-3-004 (CERN)

Alberto Di Meglio (CERN), Eric Grancher (CERN), Manuel Martin Marquez (CERN)

During the past decades, CERN has been gathering enormous amount of data. We cannot obviate that most of the times this process is costly in terms of technical and human resources. It is a fact, however, that the exploitation of the collected data, in other words, the extraction of potential benefits from our data investments, has been pushed into the background or has been placed on the bottom of our priorities. Data is the new soil and therefore it requires nurturing, enriching and managing. Obviously this will require additional efforts but at the same time it is clear that those efforts will generate important value. Within this context, the CERN openlab is working on defining the major ICT Challenges that the Experiments and the LHC engineering teams will have to face in the coming years leading up to run 2. One of the Challenges identified is focused on the use of Data Analytics methods and technologies to address large scale data and metadata analysis. This workshop represents an opportunity to collect information about how Data Analytics is already used at CERN or planned to be used, what use cases are of interest within CERN at large and what technologies exist today. This information will provide input to the discussion about activities and priorities for the current and next phase of the CERN openlab collaborations.

1 Hadoop as foundation for scientific data analytics

Speaker: Mr Bernard Doering (Intel)

2 Analytics technology and architecture to manage velocity and variety, discover relationships and classify huge amount of data

Speaker: Mr Maurizio Sallusti (SAS)

15:00 Coffee Break

3 An efficient platform for sensor data storage and manipulation

Speaker: Mr Mathias Herberts (Cityzen Data)