Day: June 4, 2026

Excited to share that our NWO OTP project DESIRE has been accepted!

Posted on by Benny Akesson

Together with ASML, University of Amsterdam, Leiden University, and TNO-ESI, we are starting a new research project on design-space exploration for complex distributed cyber-physical systems. Thank you ASML and TNO-ESI for contributing to the project, and to Philips, Canon Production Printing, Thales, Vanderlande, Eindhoven University of Technology, and University of Twente for joining the user committee.

Design-space Exploration for Complex Distributed Cyber-Physical Systems (DESIRE) builds on our earlier work in DSE 2.0, extending it toward an advanced holistic and automated approach to exploring alternative hardware platforms, software changes, and mappings — helping engineers answer critical what-if questions on performance and cost in increasingly complex systems. In particular, we will focus on:
1) Capturing realistic system behavior from traces while scaling to industrial systems with partial observability and complex environments
2) Bridging software and hardware characterization to enable model-based exploration of performance across heterogeneous platforms.
3) Handling extremely large, heterogeneous, multi-objective design spaces.

At the same time, it’s great to see how earlier results are already being picked up, matured, and experimented with in practice by TNO-ESI and ASML, closing the loop between academic research and industrial impact.

Looking forward to this next step in the collaboration!

The announcement of the grant from NWO is available here.

Reflections on a PhD Defense: Real-Time Guarantees in the Edge–Cloud Continuum

Posted on by Benny Akesson

Today, I served on the PhD committee of Nasim Samimi, who defended her dissertation titled “Edge-Cloud-Assisted Real-Time Cyber-Physical Systems.” This work addresses the challenge of providing predictable real-time guarantees for cyber-physical systems deployed across the edge–cloud continuum. As CPS increasingly rely on distributed, shared, and dynamic infrastructures, traditional design-time schedulability analysis becomes insufficient. The dissertation proposes a set of online admission control, scheduling, and orchestration techniques that provide per-job deadline guarantees and controlled service degradation under bursty workloads. The main contributions span formal job-level admission control for multicore servers, weakly-hard real-time guarantees using (M,K)-firmness, and practical deployment mechanisms for real-time workloads in Kubernetes-based edge–cloud platforms. Together, these contributions aim to bridge the gap between real-time theory and modern cloud-native practice.

I very much enjoyed reading this dissertation, as it tackles an important problem at the intersection of real-time systems, cyber-physical systems, and edge–cloud computing. I particularly appreciate the combination of solid theoretical foundations in the early chapters with increasingly practical contributions in the later chapters. A great example of this is the KubeDeadline technology, which extends Kubernetes to schedule Linux containers according to the well-known SCHED_DEADLINE policy and guarantee them a portion of CPU bandwidth with bounded latency. This work successfully translates classic real-time scheduling concepts into modern edge-cloud software architectures.

The defense went well, and shortly after the beadle pronounced the end of the defense (“Hora est!”), Nasim became Dr. Samimi. Congratulations on this achievement! It was a pleasure to serve on this committee, and I wish Nasim all the best in her future career.