Author: Benny Akesson

What if we could develop the next-generation of cyber-physical systems with all the bells and whistles faster and more cost-effectively than the previous, while still ensuring that they work correctly? Well, the truth is that industrial cyber-physical systems, such as lithography machines, x-ray machines, production printers, radars, and cars, are getting increasingly complex and difficult to efficiently design, implement, and evolve. Addressing this complexity through new design methodologies has been the common denominator throughout my research career, spanning almost two decades and including both fundamental research in academia and applied research in the Dutch high-tech systems industry. I believe that model-based design methodologies are key to addressing complexity and have many years of experience modelling hardware and software at different levels of abstraction and in a variety of formalisms and use them to generate artifacts, such as code or documentation, or analyze and optimize non-functional properties of systems, such as timing behavior or energy consumption. I enjoy the puzzle of looking at industry challenges, and defining and leading the research needed to address them through a combination of fundamental and applied research projects and programs. I also love working with people and organizations to sustainably embed the developed knowledge and technology, both in industry and academia, turning research results into impact and managing complexity step by step.

NWO Grants Funding for iCARe Project

Posted on by Benny Akesson

I am pleased to announce that the iCARe project (“Integrated indulgent Control Architecture design”) has been officially granted by NWO under the NXTGEN Hightech programme. The project brings together leading academic and industrial partners to rethink how high‑tech motion systems, such as those used in semiconductor manufacturing, are designed and optimized. With a total project budget of €3.3 million, iCARe aims to develop a radically new integrated control architecture that jointly considers servo control, computational hardware, and power electronics. This approach will enable next‑generation machines to achieve unprecedented accuracy and throughput while remaining cost‑effective, an essential step for future semiconductor technologies.

I will contribute to this project in my role as part-time professor at the University of Amsterdam (UvA). Together with partners from TU/e and ASML, UvA researchers (me, Andy Pimentel, and a PhD student) will develop innovative computational platform architectures, including new scheduling strategies and automated design‑space‑exploration tools that directly link computing performance to control‑system quality. This contribution is vital for enabling high‑precision control at extreme speeds and for integrating computing considerations into the heart of system‑engineering decisions. The project spans six years and will support collaborative research across multiple disciplines.

Congratulations to the iCARE consortium for securing this competitive funding and we look forward to working with you on this next step forward in high‑tech system design.

Read more in the official announcement from NWO.

Call for Special Session Proposals – ESWEEK 2026

Posted on by Benny Akesson

As Special Session Co-chair it is my pleasure to invite Special Session proposals for ESWEEK 2026, the premier event bringing together the embedded systems, software, and cyber-physical systems communities.

Special Sessions are a great opportunity to:
✅ Highlight emerging research directions
✅ Bring together interdisciplinary communities
✅ Foster discussion on timely and impactful topics

We welcome proposals from academia and industry covering innovative, forward-looking, and cross-cutting themes.

📌 Learn more and submit your proposal:
👉 https://esweek.org/call-for-special-session-proposals/
🌐 General information: https://esweek.org

If you are passionate about shaping the technical program of ESWEEK and sparking vibrant discussions, we strongly encourage you to submit a proposal!

Bruno Dzikowski Successfully Defends Master’s Thesis on Performance Prediction

Posted on by Benny Akesson

Yesterday, Bruno Dzikowski successfully defended his master’s thesis titled “Practical Recommendations for Accurately Predicting Performance Degradation Caused by Memory Contention” The thesis addresses the challenge of predicting performance in microservice-based architectures for cyber-physical systems (CPS) running on multi-core platforms, where resource contention significantly impacts accuracy. Existing methods model interference sensitivity and contentiousness but lack practical implementation guidelines.

 

Bruno’s work introduces a compositional performance prediction framework with three key contributions: 1) a validated contentiousness profiling component, 2) an analysis of how system configuration affects prediction accuracy, and 3) the design and implementation of an experimental testbed. Tested across 195 co-location scenarios, the approach achieves high accuracy (median error ≈ 1.4%), demonstrating its effectiveness for forecasting microservice performance.

We are very proud of the excellent research Bruno conducted during his internship with TNO-ESI, which resulted in an outstanding thesis that was confidently presented and defended. We thanks Bruno for the excellent collaboration and wish him all the best for his future career.

Celebrating Dr. Panos Giannakopoulos’ Dissertation Defense

Posted on by Benny Akesson

Congratulations to the newly minted Dr. Panagiotis (Panos) Giannakopoulos, who has successfully defended his dissertation, “Predictable Application Performance in Resource Clusters” The dissertation tackles the challenge of meeting strict Round-Trip Time (RTT) deadlines for time-sensitive applications in heterogeneous, resource-constrained edge environments by developing lightweight, accurate performance predictors. These predictors leverage selected system metrics and machine learning models to anticipate execution time and variability, enabling proactive scheduling and load balancing that improve efficiency and reduce resource waste, with demonstrated success on Electron Microscopy workloads in Kubernetes-based clusters.

This research was conducted as part of the NWO ADAPTOR project, co-funded by Thermo Fisher Scientific and ASTRON. I have had the pleasure of serving on the user committee for this project over the past couple of years and was honored to be invited to join the Ph.D. committee. Over the years, Panos has presented his work at TNO-ESI several times in various settings and was also invited to share his insights at Thales. Panos will now continue his work as a postdoctoral researcher at TU/e.

Hyperheuristic Optimization in Cyber-Physical System Design

Posted on by Benny Akesson

Today, we proudly celebrate Lars van der Water’s successful defense of his Master’s thesis, Exploring Vast Design Spaces with Hyperheuristics: Theoretical Foundations and Autotuning Implementation, at the University of Amsterdam. This work has been conducted in connection with the DSE2.0 project, a research collaboration between University of Amsterdam, Leiden University, and ASML, co-funded by NWO and TNO-ESI as a part of the Mastering Complexity (MasCot) Program.

Lars’ thesis addresses the growing complexity in designing Distributed Cyber-Physical Systems, which are increasingly vital to infrastructure and industry. Traditional Design Space Exploration methods struggle with scalability, algorithm selection, and parameter tuning, creating a bottleneck in efficient exploration of system designs. To overcome this, this work explores hyperheuristics (HHs) as a higher-level domain-agnostic approach to automate the selection and tuning of metaheuristics.  Key contributions include a modular framework for integrating HH strategies, and empirical insights into the trade-offs between performance, effort, and computational cost in autotuning. Experiments show promising results for auto-tuning of simpler meta-heuristic search algorithms like Gravitational Search and Particle Swarm Optimization, but revealing limitations with more complex ones like Genetic Algorithms.

We sincerely thank Lars for the excellent collaboration and wish him all the best in the next chapter of his career!

Paper on Parallelism in dCPS Workload Modeling Accepted at Euromicro DSD 2025!

Posted on by Benny Akesson

I am thrilled to announce that the paper “Unraveling Parallelism in Automated Workload Modeling for Distributed Cyber-Physical Systems” has been accepted for publication at the 28th Euromicro Conference Series on Digital System Design (DSD). This paper was first-authored by Faezeh Sadat Saadatmand and is a result from the DSE2.0 project, a collaboration between University of Amsterdam, Leiden University, and ASML.

The paper addresses the problem of limited exploration of software-level parallelism in distributed Cyber-Physical Systems, due to fixed execution orders in current workload models used in design-space exploration. It proposes refined workload models based on execution traces that capture both inter- and intra-process dependencies, enabling safe task reordering and parallel execution without modifying the software. A case study on the ASML Twinscan lithography machine demonstrates performance improvements while maintaining functional correctness.

Reflections on RTAS 2025 from the General Chair

Posted on by Benny Akesson

It has been a pleasure to serve as the General Chair of the 31st IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS 2025). RTAS is a top-tier conference on real-time systems that is a part of the CPS-IoT Week. This year, CPS-IoT week was hosted at UC Irvine, USA, and it was one of the most well-attended instances so far with over 550 registrations from all over the world.

Here are some personal highlights:

  • Keynote: “Trusted AI on Mars” by Dr. Steve Chien: This keynote discussed the challenge of controlling the Perseverance rover on Mars. The original planner was time-triggered and struggled to efficiently adapt to unexpected changes, e.g. in temperature and battery state. The core of the presentation covered the design, analysis, prototyping and testing of a new AI-based Onboard Planner that was deployed in October 2023. This planner enabled the schedule to be revised on average 16 times per day to manage resources, such as energy, more efficiently and maximize the scientific operations conducted by the rover. This presentation was very interesting to the real-time systems community as it focused on planning inside a heavily resource-constrained cyber-physical system in a dynamic environment far away from earth. It was interesting to hear the challenges of getting new technology adopted in such a critical system, where the cost of verification and validation is a key driver for decision-making.
  • Inaugural CPS-IoT Debate: We have all attended bland panel discussions at conferences. This was different, as it had the format of an Oxford debate and discussed whether the inherent complexity of modern engineering challenges renders exhaustive mathematical analysis overkill, and that an iterative, adaptive design approach should be prioritized—even for life-critical systems. The format, the existential nature of this question for our community, and the excellent choice of the debate team resulted in an engaging session with high audience participation that sparked conversations throughout the day. I strongly encourage other conferences to try out this format.
  • RTAS Technical Sessions: The technical sessions of RTAS are always of high quality and interesting. I particularly enjoy the papers that help bring theory into practice. Here are a few papers that stood out to me:
    • LiME: The Linux Real-Time Task Model Extractor by Bjorn Brandenburg et al. describes a tool to extract real-time task models from real-time threads in a Linux environment.  LiME runs on unmodified Linux kernels and requires neither knowledge of real-time theory nor familiarity with Linux internals to be used effectively. Such a tool can significantly reduce the engineering, modeling, and analysis effort required to develop real-time systems whose timing behavior can be formally verified.
    • Reconciling ROS 2 with Classical Real-Time Scheduling of Periodic Tasks by Harun Teper et al. explains how minor changes to the event executor of ROS2 makes a large body of research results from classical real-time scheduling theory directly applicable to ROS 2. This enables analytical bounds on the worst-case response time and the end-to-end latency, outperforming bounds for the default ROS 2 executor in many scenarios.
    • CROS-RT: Cross-Layer Priority Scheduling for Predictable Inter-Process Communication in ROS 2 by Kim et al., which won the Best Paper Award, addresses the challenge of providing real-time guarantees in ROS2 due to unpredictable delays and priority inversions across ROS 2’s multi-layered communication architecture. They present a cross-layer scheduler explicitly designed to tackle the unpredictability in ROS 2 inter-process communication that has been implemented and evaluated on the current stable release of ROS 2.

These works all make significant strides in bringing theory to practice. Just imagine what happens if you combine them all!

All in all, it was a very successful event thanks to the excellent work done by Program Chair Tam Chantem, Program Co-chair Geoffrey Nelissen, the General Co-chairs of CPS-IoT Week Mohammad Al Faruque and Yasser Shoukry, Local Arrangement Chairs Fadi Kurdahi and Halle Gonzales, and many others involved in the organization. Of course, RTAS would not have been possible without the many authors who submitted their work and the members of the TPC who took the time to read the submissions and provide high-quality reviews.

 

Highlights from the RTAS Awards Ceremony

Posted on by Benny Akesson

The Award Ceremony of the 31st IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS) has concluded, and it is our pleasure to announce the highlights of this year’s awards.

The RTAS 2025 Technical Program Committee nominated four papers for awards, evaluating them based on novelty, presentation, applicability to real-world applications/systems, and relevance and completeness of experimental evidence. The four papers were selected as Outstanding Papers and candidates for the Best (Student) Paper Award.

Best Paper Award
CROS-RT: Cross-Layer Priority Scheduling for Predictable Inter-Process Communication in ROS 2
Authors: Sohyun Kim, Juho Song, Kilho Lee, Sangeun Oh, and Hoon Sung Chwa

This paper tackles the challenges of achieving real-time guarantees in ROS2 due to unpredictable delays and priority inversions. CROS-RT, a cross-layer scheduler, ensures consistent priority-based scheduling across application, middleware, and kernel layers. Experiments show that CROS-RT significantly improves communication predictability, reducing the worst-case response time compared to baseline ROS2. The Best Paper Award committee was impressed by this paper’s practical significance and immediate, as well as long-term, impact on the field.

Best Student Paper Award
A Unified Framework for Quantitative Cache Analysis
Authors: Sophie Kahlen and Jan Reineke

This work unifies two approaches to cache analysis for non-LRU policies. It is applicable to microarchitectures with timing anomalies and enhances WCET analysis using existing persistence analyses for LRU. Experiments demonstrate that the precision of cache analysis for FIFO and MRU is comparable to that of LRU. The Best Paper Award committee viewed this paper as an excellent example of a well-integrated blend of theoretical results and implementation efforts, which embody the spirit of RTAS.

The Best Reviewer Committee evaluated six nominated reviews/reviewers based on criteria like review quality, completeness, and helpfulness to the authors. Four reviewers were recognized as Outstanding Reviewers and candidates for the Best Reviewer Award.

Best Reviewer Award
Zoe Stephenson, Rapita Systems, UK

RTAS is grateful to all members of the Technical Program Committee who volunteer their time to review submitted papers. It is particularly rewarding when industry members contribute to the conference and stand out in terms of reviewing excellence, both in thorough reviews and active participation in discussions. Thank you, Zoë!

We want to thank the members of the Award Committees and congratulate all award recipients on their achievements and thank you for your contributions to another successful RTAS!

Benny Akesson, General Chair
Tam Chantem, Program Chair
Geoffrey Nelissen, Vice Program Chair

 

 

New Methodology for Efficient Design Space Exploration in Next-Gen Cyber-Physical Systems

Posted on by Benny Akesson

I’m excited to share that our journal article “CompDSE: A Methodology for Design Space Exploration of Computing Subsystems within Complex Cyber-Physical Systems” has been accepted for publication in IET Cyber-Physical Systems: Theory and Applications! The article, first-authored by Faezeh Sadat Saadatmand, outlines the model-based Design Space Exploration (DSE) approach we used in the DSE2.0 project. This project is a collaboration between Leiden University, the University of Amsterdam, and ASML, and is co-funded by NWO and TNO-ESI.

Our work addresses the need for efficient DSE techniques to evaluate potential design decisions and their impact on non-functional aspects like performance, reliability, and energy consumption in next-gen complex distributed cyber-physical systems (dCPS).

In the article, we introduce CompDSE, a methodology designed to facilitate the DSE of complex dCPS, with a focus on the computing subsystems. CompDSE uses abstract models of the application workload, computing hardware platform, and workload-to-platform mapping, all automatically derived from runtime trace data. These models are integrated into a discrete event simulation environment to explore various design points.

We demonstrate the effectiveness of our methodology through a case study on the ASML Twinscan lithography machine, a complex industrial dCPS. The results show potential performance enhancements by optimizing computing subsystems while considering physical constraints. Each design point evaluation takes less than a minute, highlighting CompDSE’s efficiency and scalability in tackling complex dCPS with large design spaces.

Highlights from TNO-ESI at ICT.OPEN 2025

Posted on by Benny Akesson

NWO ICT.OPEN 2025 took place in the Jaarbeurs in Utrecht on April 15 and 16. In retrospect, I think it was the best ICT.OPEN I have visited so far. It was also the most popular edition in modern times, with over 500 registered participants and another 200 people wanting to register, but who could not be accommodated. It was particularly nice to see that systems research is now well represented at the conference again, thanks to the CompSys community and organizations like TNO. TNO was highly visible at the event this year with representation from several research groups within the unit ICT, Strategy and Policy. Below are some highlights focusing on the involvement from my dear group TNO-ESI:

  • Keynote: I gave a keynote titled “Engineering the Future: Addressing System Complexity in High-Tech Equipment”, which described the challenge of increasing system complexity in high-tech equipment and how TNO-ESI addresses this challenge in an open innovation ecosystem by developing engineering methodologies based on model-based engineering, formal methods, and artificial intelligence. Two examples were given of such methodologies, ComMA and Renaissance, highlighting the collaborations in the innovation chain and describing the industry impact.  Immediately after the keynote, I also participated in an NWO Panel session about partnerships in ICT Research, where challenges and best practices for research collaborations were discussed among the panelists and with the audience.
  • Mastering Complexity Track: Rosilde Corvino and Nan Yang co-chaired the track “Mastering Complexity for Cyber-Physical Systems”, which featured three presentations: one invited industry talk and two peer-reviewed research contributions. The invited presentation was delivered by Alok Lele, Project Manager at ASML Software Research. He shared insightful perspectives on leveraging Generative AI to modernize the software of ASML systems. His concept of continuous and iterative micro-modernization sparked an engaging discussion among the audience. In addition, PhD candidates Faezeh Sadat Saadatmand and Ameneh Naghdi Pour presented their research on design-space exploration and system diagnosis, respectively. The session was interactive and discussed emerging methodologies and challenges in managing complexity in cyber-physical systems.
  • Research results: Emile van Gerwen and Micha Lipplaa demonstrated how using chain-of-thought prompting with a Large Language Model (LLM) in combination with semantic search helps Philips Healthcare in their risk assessment of incoming complaints. Their work concluded that compared to both keyword search and semantic search without an LLM knowledge extraction pre-processing step, a combined approach clearly shows the best results.

I would like to thank all organizers for a lovely event, particularly the Program Co-chairs Mitra Nasri and Vadim Zaytsev for putting together a fantastic program.