Delft University of Technology Master of Science Thesis in Embedded Systems Deriving Timing Properties from System Traces using Data-driven Techniques S¸erban Vadineanu˘ Supervised by Dr. Mitra Nasri Embedded Networked Systems Deriving Timing Properties from System Traces using Data-driven Techniques Master of Science Thesis in Embedded Systems Embedded and Networked Systems Group Faculty of Electrical Engineering, Mathematics and Computer Science Delft University of Technology Mekelweg 4, 2628 CD Delft, The Netherlands S¸erban V˘adineanu
[email protected] [email protected] TU Delft Student Number: 4824989 Supervised by Dr. Mitra Nasri 23.07.2020 Author S¸erban V˘adineanu (
[email protected]) (
[email protected]) (TU Delft Student Number: 4824989) Title Deriving Timing Properties from System Traces using Data-driven Techniques MSc Presentation Date 03.08.2020 Graduation Committee dr. ir. Fernando Kuipers (chairman) Delft University of Technology dr. Mitra Nasri Delft University of Technology and Eindhoven University of Technology dr. Jan Rellermeyer Delft University of Technology Abstract With the growth in the complexity of real-time embedded systems, there is an increasing need for tools and techniques to understand and compare the observed runtime behavior of a system with the expected one. Since many real- time applications require periodic interactions with the environment, one of the fundamental problems in guaranteeing/monitoring their temporal correctness is to be able to infer the periodicity of certain events in the system. The prac- ticability of a period inference tool, however, depends on both its accuracy and robustness (resilience) against noise in the output trace of the system, e.g., when the system trace is impacted by events that have a non-deterministic nature such as the presence of aperiodic tasks, release jitters, and runtime execution-time variations of the tasks.