Gastvortrag "Online Experiment-Driven Adaption", Dr. Ilias Gerostathopoulos (TU München)

11.01.2019, 15:00 - 16:00

Wir dürfen heute im DFKI Gebäude (D3 2) im VisRoom Herrn Dr. Ilias Gerostathopoulos von der TU München begrüßen und freuen uns auf einen spannenden Vortrag zum Thema "Online Experiment-Driven Adaption". Alle Interessierten sind herzlich zu Vortrag und Diskussion eingeladen!


As modern systems become larger, more complex and customizable, it is difficult to fully model their internal workings in advance in here optimization based on operational data and experimentation. In this talk, I will present the main ideas behind Online Experiment-Driven Adaptation (OEDA), an approach whereby systems are adapted and configurations are evaluated by controlled experiments in production environments using advanced data analysis and statistical methods. In particular, I will describe the main concepts of OEDA, along with an example of a complex, hardto-model system that is amenable to online optimization via controlled experiments— the CrowdNav self-adaptation model problem. I will also describe three different types of costs in online experimentation and discuss the tradeoffs in terms of the different costs of using three different optimization algorithms: Bayesian optimization, factorial design, and local search.


Dr. Ilias Gerostathopoulos obtained his PhD in march 2012 at Department of Distributed and Dependable Systems at Charles University in Prague on „Model Driven Development of Software-Intensive Cyber-Physical Systems“. Since January 2016 he works at Technical University of Munich as an postdoctoral researcher. His emphasis in research and publications is about „Software Architecture“, „Self-Adaptive Systems“ and „Big Data Analytics“. Current projects are the „TUM Living Lab Connected Mobility“ as well as „Collaborative Embedded Systems“. At Technical University of Munich he also gives lectures about „Internet of Things and Services“