Skip to main content
  1. Research/

Energy-, Latency- And Resilience-aware Networking (e.LARN)

LARN Logo

This project is part of the DFG (Deutsche Forschungsgemeinschaft) priority programme SPP 1914 “Cyber-Physical Networking”. It started as LARN in October 2016 and after successful application for the second funding phase of the SPP, this continuation project started in January 2020 (DFG project number 315036956). It is carried out in cooperation with Department of Computer Science 4 at Friedrich-Alexander-Universität Erlangen-Nürnberg.

Vision
#

We propose to develop transport channels for distributed cyber-physical systems. Such channels need to be energy-, latency-, and resilience-aware; i.e. the latency as seen by the application must be predictable and in certain limits, e.g. by balancing latency and resilience, be guaranteed. At the same time, the energy aspects must be considered, as CPS devices often have limited access to power sources. Achieving these awareness-properties is only possible by an innovative transport protocol stack and an appropriate fundament of operating system and low level networking support. Thereto the project unites the disciplines Operating Systems / Real-Time Processing and Telecommunications / Information-Theory.

Reliable Networking Atom (RNA) Architecture
Reliable Networking Atom (RNA) Architecture

Project target is the evolution of the PRRT (predictably reliable real-time transport) transport protocol stack towards a highly efficient multi-hop-protocol with transparent transmission segmentation. This is enabled by an interdisciplinary co-development with a latency-aware operating system kernel incl. wait-free synchronisation and the corresponding low level networking components. The statistical properties of the entire system (RNA, “reliable networking atom”) shall be optimised and documented.

software-defined networking testbed for validation of the system in a real-world wide area network scenario is available. The developed components are introduced during the workshops organised by the priority programme SPP1914 “Cyber-physical Networking” and is made available to other projects during the entire run-time of the priority programme.

Objectives
#

First phase:

  • Develop a latency- and resilience-aware atomic unit for cyber-physical networks.
  • Optimise the cross-layer communication while maintaining separability.
  • Validate the approach in theory and experiments.
  • Document the statistics of the predictable quality of communication (QoC).

Second phase:

  • Develop a latency-, resilience- and energy-aware atomic unit for cyber-physical networks.
  • Optimise communication across all layers (vertical) and between hosts (horizontal).
  • Extract, refine and validate models for latency, resilience and energy aspects of cyberphysical networks.
  • Document the statistics of the predictable quality of communication (QoC) in selected CPN applications.

Solutions & Results
#

Activities
#

  • Co-Organization of the IEEE Workshop on Cyber-Physical Networks (2019, 2020).
  • Contributions to the “Network Support for Gain Scheduled Control” BarCamp started in November 2018 in Aachen.
  • Organization of the “Hands-On Cyber-Physical Networking” BarCamp within the SPP1914 Winter School in Arosa.

Presentations
#

Publications
#

The publications can also be found on Google Scholar.

  1. 2024 #

  2. 2023 #

  3. 2022 #

  4. Resource-demand Estimation for Edge Tensor Processing Units

    Benedict Herzog, Stefan Reif, Judith Hemp, Timo Hönig, Wolfgang Schröder-Preikschat
  5. 2021 #

  6. AnyCall: Fast and flexible system-call aggregation

    Luis Gerhorst, Benedict Herzog, Stefan Reif, Wolfgang Schröder-Preikschat, Timo Hönig
  7. Low-Level Design of Energie-Efficient HARQ at the Transport Layer

    Mikolai-Alexander Gütschow
    Bachelor's Thesis
  8. Towards automated system-level energy-efficiency optimisation using machine learning

    Benedict Herzog, Stefan Reif, Fabian Hügel, Timo Hönig, Wolfgang Schröder-Preikschat
  9. Automated Selection of Energy-efficient Operating System Configurations

    Benedict Herzog, Fabian Hügel, Stefan Reif, Timo Hönig, Wolfgang Schröder-Preikschat
  10. Annotate once — analyze anywhere: Context-aware WCET analysis by user-defined abstractions

    Simon Schuster, Peter Wägemann, Peter Ulbrich, Wolfgang Schröder-Preikschat
  11. AI Waste Prevention: Time and Power Estimation for Edge Tensor Processing Units: Poster

    Stefan Reif, Benedict Herzog, Judith Hemp, Wolfgang Schröder-Preikschat, Timo Hönig
  12. The price of meltdown and spectre: Energy overhead of mitigations at operating system level

    Benedict Herzog, Stefan Reif, Julian Preis, Wolfgang Schröder-Preikschat, Timo Hönig
  13. 2020 #

  14. Deep Adaptive Hybrid Error Coding

    Ashkan Taslimi Baboli
    Master's Thesis
  15. Nearly symmetric multi-core processors

    Stefan Reif, Benedict Herzog, Fabian Hügel, Timo Hönig, Wolfgang Schröder-Preikschat
  16. X-Leep: Leveraging cross-layer pacing for energy-efficient edge systems

    Stefan Reif, Benedict Herzog, Pablo Gil Pereira, Andreas Schmidt, Tobias Büttner, Timo Hönig, Wolfgang Schröder-Preikschat, Thorsten Herfet
  17. Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators

    Stefan Reif, Benedict Herzog, Judith Hemp, Timo Hönig, Wolfgang Schröder-Preikschat
  18. 2019 #

  19. Earl: energy-aware reconfigurable locks

    Stefan Reif, Phillip Raffeck, Heiko Janker, Luis Gerhorst, Timo Hönig, Wolfgang Schröder-Preikschat
  20. Energy-demand estimation of embedded devices using deep artificial neural networks

    Timo Hönig, Benedict Herzog, Wolfgang Schröder-Preikschat
  21. Enabling wireless network support for gain scheduled control

    Sebastian Gallenmüller, René Glebke, Stephan Günther, Eric Hauser, Maurice Leclaire, Stefan Reif, Jan Rüth, Andreas Schmidt, Georg Carle, Thorsten Herfet
  22. 2018 #

  23. A predictable synchronisation algorithm

    Stefan Reif, Wolfgang Schröder-Preikschat
  24. 2017 #

  25. In the Heat of Conflict: On the Synchronisation of Critical Sections

    Stefan Reif, Timo Hönig, Wolfgang Schröder-Preikschat
  26. 2016 #

People and Partners
#

Timo Hönig (FAU), Adwait Datar (TUHH), Andreas Schmidt (SIC), Florian Rosenthal (KIT), Stefan Reif (FAU), Thorsten Herfet (SIC) at the “Hands-On Cyber-Physical Networks” BarCamp of the DFG SPP1914 Winter School, January 2018  

Telecommunications Lab
#

Chair for Distributed Systems and Operating Systems
#

  • Prof. Dr.-Ing. Wolfgang Schröder-Preikschat
  • Stefan Reif, MSc.
  • Dr.-Ing. Timo Hönig
  • Dr.-Ing. Peter Ulbrich

1st IEEE Workshop on Cyber-Physical Networks Co-Organizers
#

  • Dr.-Ing. Timo Hönig (Friedrich-Alexander-University Erlangen-Nürnberg)
  • Prof. Dr.-Ing. Klaus Wehrle (RWTH Aachen University)
  • Dr. sc. Sebastian Trimpe (Max Planck Institute for Intelligent Systems)

BarCamp Aachen Contributors (EdgeSys2019 Paper)
#

  • Sebastian Gallenmüller, MSc. (Technical University of Munich)
  • René Glebke, MSc. (RWTH Aachen University)
  • Dr.-Ing. Stephan Günther (Technical University of Munich)
  • Eric Hauser, BSc. (Technical University of Munich)
  • Maurice Leclaire, MSc. (Technical University of Munich)
  • Jan Rüth, MSc. (RWTH Aachen University)

BarCamp “Hands-On Cyber-Physical Networking” Contributors
#

  • Adwait Datar, MSc. (TUHH)
  • Christine Kloock, MSc. (TUHH)
  • Florian Rosenthal, MSc. (KIT)