Vinodh Venkatesan  Vinodh Venkatesan photo       

contact information

Data Storage Systems Research
IBM Research - Zurich
  +41dash44dash724dash86dash38

links

Professional Associations

Professional Associations:  IEEE

more information

More information:  IBM Research - Zurich  |  Cognitive Storage  |  Tiered Storage  |  Storage Reliability  |  DOME

profile


 

Biography

Vinodh Venkatesan received D.Sc. degree from EPFL in 2012 for his thesis titled Reliability Analysis of Data Storage Systems, which was done in collaboration with IBM Research. Prior to that, he received B.Tech. degree in electrical engineering from IIT Madras in 2006, and M.Sc. degree in electrical engineering and information technology from ETH Zurich in 2008. Since 2008 he has been working at IBM Research on data storage systems research. He is a recipient of two Best Paper Awards for his work on reliability analysis of data storage systems in MASCOTS 2011 and CTRQ 2017 conferences. Between 2014 and 2017, he was the IBM Research lead for the work package on Access Patterns in the DOME project, a joint research project with ASTRON, the Netherlands Institute for Radio Astronomy, to carry out research needed to develop the Square Kilometre Array (SKA) radio telescope. The SKA will be the world's most sensitive radio telescope, which is expected to be built by the year 2024, and it is estimated to generate one exabyte of data per day. The Access Patterns work was focused on the data storage aspects of the project and has made significant progress in storage systems modeling, resulting in an exascale multi-tiered storage systems planning and optimization tool called ExaPlan as well as the development of the concept of Cognitive Storage. Cognitive Storage, which has received worldwide press coverage (search "Cognitive Storage" for more), asserts that each piece of data has value (or relevance) to the user and that significant efficiency can be gained by optimizing storage policies based on data relevance as well as data popularity. Vinodh's current research interests include machine learning algorithms for data relevance estimation and access prediction in cognitive storage systems, performance and reliability modeling, and optimization of multi-tiered storage systems under cost constraints.

Current Work

- Algorithm design for data relevance estimation and access prediction in cognitive storage systems
- Mathematical modeling and performance analysis of exascale multi-tiered data storage systems
- Reliability analysis of data storage systems