ENHANCE: Enabling Technologies and Dependability in Cyber-Physical Systems

Attention: This workshop is in a separate building (see above directions).

This workshop is part of a three day segment in HiPEAC 2024 with a spotlight on bridging between contributing communities to future large-scale safety-critical systems (also known as CPS). Comprising FORECAST, STEADINESS & ENHANCE, the Segment overview is described above in the ‘Programs’ tab.

ENHANCE encourages participation from enabling technology communities including IoT, AI and Big Data. Product-side and market influencers, such as from product-lines and policy making, are also invited to participate.

Session co-chaired by Danh Le Phuoc (Technical University of Berlin) & Spyros Lalis (University of Thessaly).

Agenda:

10:00 – 10:15 Welcome / setup

10:15 – 10:35IoT-Edge-Cloud Continuum for Manufacturing, Dr. Ovidiu Vermesan, Chief Scientist, SINTEF

10:35 – 10:55 *P4-based Decentralized Swarm Intelligence for Smart Factory Scenario*, Michelangelo Guaitolini, CNIT, Italy

11:00 – 11:30 Coffee break

11:30 – 11:50Towards a Deep Investigation of Cybersecurity Issues in Cyber-Physical Systems Using a Novel Graph Neural Network-Based Threat Analysis Approach, Abdelkader Magdy Shaaban, Samir Moustafa, and Christoph Schmittner, Center for Digital Safety and Security, Austrian Institute of Technology GmbH, Vienna, Austria and Faculty of Computer Science, University of Vienna, Austria

11:50 – 12:10Methodology for Transforming a Local Safety-Critical Cyber-Physical System into a Distributed Safety-Critical Solution, Krzysztof Oborzyński, Philips, and Astrid Rakow, DLR

12:10 – 12:30End-to-end Autonomic Management of Cloud-Edge Continuum Systems using Reinforcement Learning: Design Approach and Formulation, Theodoros Aslanidis, Andreas Chouliaras, John Byabazaire and Dimitris Chatzopoulos, University College Dublin

12:30 – 13:00 Panel Discussion

13:00 End of workshop

*A half-day workshop.

Workshop Focus & Topics of Interest

Cyber-physical systems (CPS) have been adopted in many industrial sectors thanks to development of several new enabling technologies both on software and hardware side. Examples of topics that play a key role in advancing CPS are: Artificial Intelligence, model-driven software engineering, formal modeling and verification, wireless communication, novel embedded and Edge controllers. These technologies are evolving at a fast pace. At the same time, dependability is a “must have” requirement for the entire CPS life cycle. However, as CPS become more prominent across the globe and increasingly depend on the interplay between the Edge and the Cloud, building trustworthy CPS and managing the complexity of their hierarchies of systems is probably more challenging than ever before.

The workshop seeks submissions for presentations describing practical and theoretical approaches and solutions to advance the design and implementation of trustworthy CPS spanning the Cloud-Edge-IoT continuum or parts thereof. In particular, presentations covering the following topics (but not limited to) are welcome:

• IoT, IIoT and dependability: IoT systems are a class of systems that use the Internet as the backbone technology.

  • In this topic, presentations related to bridging best of security research and IoT and IIoT are encouraged, Ex: Authentication and Authorization in IoT.

  • The Time-Sensitive Networking task group of the IEEE 802.1 working group is adding new capabilities, especially bridging wired and wireless devices. Presentations related to this topic and its impact on dependability are encouraged.

• Software Engineering methods for dependable CPS: the amount of software in CPS is growing and the key factor defining its functionality.

  • In this topic, presentations related to reducing the software engineering effort while at the same time ensuring quality for dependable CPS are encouraged.

  • However, treating the software in isolation would be short sighted. Therefore model driven approaches addressing cross domain concerns of CPS are as well encouraged.

• Artificial Intelligence and dependability: AI and CPS now go hand in hand. One cannot exist without the other.

  • In this topic, presentations related to explainability and dependability analysis of AI and ML-based algorithms in the area of CPS will be considered.
  • Another topic of special interest is distributed/swarm intelligence. Flexibility requirements have become key to CPS in Industry 4.0 context and presentations related to learning the behavior and adapting to flexible factories, based on ML based agents are encouraged.

• System of Systems: SoS are now considered a fundamental building block of CPS for advancing future safety-critical systems.

  • Topics helping bridge the SoS community to other contributing communities are encouraged. Including cross-disciplinary focuses such as safety-security-performance integrations.

• Big Data and dependability: Data is now available in abundance, for example traces of system operation at all times.

  • Topics related to use of big data to construct models for use in dependability analysis are encouraged. Process mining is one such example, which can be used to link model-based process analysis and data-oriented analysis techniques.

Presentation Submission Instructions

The workshop welcomes talks describing new ideas, work in progress or experience reports both from industry or academia. The talks can include materials already published or presented in other venues.

• Presenters prepare an extended abstract (0.5-1 page) describing presentations for an estimated duration of 20-30 minutes.
• The submission should include a title, name of presenter(s) and the description of the proposed talk (there is no specific template, please send a PDF file with the information).
• Please send the presentation proposals via e-mail to : Now closed.

Important Dates

• Submission date deadline: November 24 => Extension to 11th December
• Confirmation date : 14th December

SUPPORT THROUGH PROJECTS

This workshop is supported by the projects MLSysOps, SMARTEDGE and the TRANSACT projects.

• The MLSysOps project (https://mlsysops.eu/) has received funding from the Horizon Europe research and innovation program (Cognitive Cloud) under grant agreement No 101092912. The goal of MLSysOps is to support autonomic system management and configuration across the Cloud-Edge-IoT continuum using ML methods, tackling different aspects such as application deployment & orchestration, HW-based acceleration, storage, wireless networking and trust, while targeting two real world application use-cases in the domain of smart cities and smart agriculture.
• The project SMARTEDGE (smart-edge.eu) is supported by the European Union’s Horizon RIA research and innovation programme under grant agreement No. 101092908. SMARTEDGE aims to enable dynamic integration of decentralized edge intelligence while prioritizing reliability, security, privacy, and scalability. This will be realized through a semantic-based interplay of edge devices in a cross-layer toolchain, allowing seamless and real-time distribution of autonomous intelligence swarms. By leveraging low-latency connectivity, the project enables the development of applications that distribute processing, data fusion, and control across diverse sensors, devices, and edges.
• The TRANSACT project (https://transact-ecsel.eu/) has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 101007260. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Netherlands, Finland, Germany, Poland, Austria, Spain, Belgium, Denmark, Norway.

Discussion

Past year’s discussion was captured in a white paper entitled: Safety-Critical Collaborative Systems: Convergence to future Cyber-Physical Systems

We plan to have a similar white paper this year about recommendations for future research ideas and goals.

LINK: Shared discussion notes - added during the workshop