Sites Inria

Version française

KOPERNIC Research team

Keeping wOrst case reasoning aPpropriatE foR differeNt critICALITIES

Team presentation

A cyber-physical system (CPS) has cyber (or computational) components and physical components that communicate. The Kopernic team deals with the problem of studying time properties (execution time of a program or the schedulability of communicating programs, etc.) of the cyber components of a CPS.  The cyber components may have functions with different criticalities with respect to time and a solution should come with appropriate proofs for each criticality. A solution is appropriate for a criticality level if all functions fulfill the expectations of that criticality level.

Based on their mathematical foundations, the solutions are: either non-probabilistic when all time properties are estimated and/or bounded by numerical values or probabilistic when at least one time property is estimated and/or bounded by probability distributions.

The Kopernic team proposes a system-oriented solution to the problem of studying time properties of the cyber components of a CPS. The solution is expected to be obtained by composing probabilistic and non-probabilistic approaches for these systems.

Research themes

  • a classification of variability factors of execution times for a program with respect to the processor features.
  • a compositional rule of statistical models based on Bayesian approaches for bounds on the execution times of programs.
  • scheduling algorithms taking into account the interaction between different variability factors.
  • schedulability analyses based on the proposed scheduling algorithms.
  • deciding the schedulability of programs communicating through predictable and non predictable networks.

International and industrial relations

National collaborations: Inria (MISTIS, RITS), CNAM (MSDMA), UPEM-ESIEE (LIGM), University of Lorraine (SIMBIOT), ISAE-ENSMA Poitiers (LIAS)

International collaborations: University of York, Federal University of Bahia, NTU Singapore.

Industrial collaborations: Airbus, Thales, RTaW, Artal, Clearsy, Silkan, Sysgo, Alerion, ADCIS, EDF, Enedis.

Domain of applications:

Avionics: the time critical solutions in this context are currently based on temporal and spatial isolation of the programs and the understanding of multi/manycore interferences is crucial.

Railway: the time critical solutions in this context concern both the proposition of an appropriate scheduler and associated schedulability analyses.

Autonomous cars: the time critical solutions in this context concern the interaction between programs executed on multi/manycore processors and messages transmitted through wireless communication channels.

Drones: as in the case of autonomous cars, there is an interaction between programs and messages, allowing our results to be applied also in this context.

Keywords: Cyber-physical systems Real-time systems Embedded systems Mixed-criticality constraints Multi/manycore processors System-oriented approaches Probability theory Statistics