Zuse Institute Berlin

In the second phase of the DFG-funded Collaborative Research Centre SFB 1404 'FONDA: Foundations of Workflows for Large-Scale Scientific Data Analysis' at HU Berlin, we are researching in the sub-project 'B4: Proactive Network, I/O, and Storage Steering for Multiple DAWs on Shared Infrastructures' at ZIB in cooperation with TU Darmstadt new methods for the more efficient execution of so-called scientific data analysis workflows. This is achieved, for example, through automated, predictive distribution or migration of data objects for faster data access or through customised bandwidth allocation for less interference when several applications use the same execution platform in parallel. A connection between the project work and a doctoral project is desired and supported. Development, implementation and analysis of new methods with regard to the project objectives Testing and adapting the developed methods to cluster systems Active co-operation and coordination with the project partners, Goal-orientated, scientific work Publication of the results in conference and journal articles