The engineered systems of today are characterized by an ever increasing
complexity. This complexity is often due, not only to a large number
of compontents, but above all to heterogeneity of their components.
To deal with this heterogeneity, and with the need to protect
Intellectual Property (IP) of the authors of the components, co-simulation
proposes to not expose the models inside components, but rather to
orchestrate their simulation, using the minimal information necessary
from the components to guarantee overall correct simulation.
This thesis will work on the following problems:
1. To ensure correctness of the developed co-simulation protocols,
automata models (for example, in UPPAAL) will be built of these protocols
which are amenable to model checking.
2. The further development of the Functional Mockup Interface (FMI)
co-simulation standard by investigating exactly what information
needs to be exposed to allow for correct and efficient co-simulation.
Both the mapping onto know formalisms (such as DEVS) and semantic
adaptation will be investigated.
The relationship with the High-Level Architecture (HLA) for
distributed discrete-event simulation will be investigated.
This, and the link with DEVS may lead to new features such as hierarchical
3. The briding of the continuous-discrete gap. This is an issue in
so-called hybrid models, where continuous-time models such as differential
equations are combined with discrete-time or discrete-event models.
These typically result from the modelling of a physical system
in its interaction with a software controller and possibly a network.
In hybrid models, numerical approximations are made when discretizing
continuous models to make them computable on digital devices.
Furthermore, modelling constructs and techniques allowing state-event
location are necessary.
In this research, the primitives for modelling and co-simulation of
hybrid models will be investitgated.