Design-time optimization of runtime adaptation strategies using Reinforcement learning-based methods
| Typ | Masterarbeit | |
|---|---|---|
| Aushang | ||
| Betreuer | Wenden Sie sich bei Interesse oder Fragen bitte an: Martina Rapp (E-Mail: rapp@fzi.de, Telefon: +49-721-9654-645) |
Motivation
Self-adaptive software systems (SAS) are an important class of software applications. Examples are IoT systems and IaaS/cloud systems like scalable web services. Since Reinfocment learning (RL) and Machine learning (ML) methods have developed significantly over the past few years, we would like to try the following:
Tasks
The thesis aims to explore the idea of applying Reinforcement learning-based methods for the design-time optimization of runtime adaptation strategies.
The main tasks will be:
- Conceptualize the idea
- Formalize the idea: elaborate the theoretical foundation to apply RL methods
- Implement and evaluate the concept
Benefits
- Insight into a highly relevant field of research
- Opportunity to develop innovative technologies
- Opportunity to contribute to a scientific publication
- Very good working environment and intensive support