Research Interests:
I'am co-head of the EPI Zenith and my research interests are related to distributed data management in different contexts as explained below.
My research activities are focused on distributed data management (data replication, query processing, etc). Since 2009 I have been investigating new search and recommendation techniques for distributed data management. More precisely, I investigate new recommendation methods that exploites diversification, deployed over different types distributed architectures. The results of this research may be applied to web and scientific data sets. For instance, in Pl@ntNet project, recommendation methods based on diversification are very useful for plant identification. This research activity is supported by CNRS Mastodons Project and Numev PIA.
I'am also involved in the topic of data-intensive scientific workflows over geographically distributed clouds. The problem here is to fragment a data intensive scientific workflow among multiple cloud sites, taking into account data transfers and load balance . This joint project between the Kerdata and Zenith teams is funded by Microsoft in the context of the Joint Inria – Microsoft Research Centre. The project addresses the problem of advanced data storage and processing for supporting scientific workflows in the cloud. The goal is to design and implement a framework for the efficient processing of scientific workflows in multiple cloud sites. Our approach will leverage the cloud infrastructure capabilities for handling and processing large data volumes.