Overview of the Research Group

Welcome at the web pages of the Parallel and Distributed Systems research group (Arbeitsgruppe Parallele und Verteilte Systeme - PVS). The group has been established in October 2010 and is lead by Prof. Dr. Artur Andrzejak. Our research targets complex and distributed software, in particular data analysis systems. We primarily focus on the following domains:

Development of reliable software:

  • Testing of large-scale software, in particular of data analysis systems
  • Detection and isolation of latent and security-critical software defects (esp. software aging)
  • Diagnosis of configuration errors in complex software systems
  • Performance optimization of data-centric applications.

Efficient data processing and analysis:

  • Efficient programming and low-code approaches for data science
  • Algorithms and tools for scalable data wrangling/data processing
  • Cloud-based resource provisioning.

In search for solutions we combine approaches from statistics, machine learning, performance evaluation, software engineering and others.

Current Research Projects

Projects related to developing reliable software include:

  • Efficient testing in large-scale projects, in particular databases (cooperation with SAP SE, Walldorf)
  • Detection and diagnosis of memory leaks in complex applications
  • Performance optimization of data-centric Java applications
  • Understanding configuration dependencies in complex software systems.

Current projects related to efficient data analysis:

  • Approaches and tools for rapid data preprocessing/wrangling (partially in cooperation with BASF SE)
  • Efficient code development for data science via code recommendations and DSLs.

Researchers interested in our work and students who would like to participate in these projects are encouraged to contact us for further details.

Our industrial and academic collaboration partners include: