Distributed Embedded Systems
21 - 24 November 2005
Venue: Lorentz Center@Oort
If you are invited or already registered for this workshop, you have received login details by email.
In the area of embedded systems, we are facing the following major changes:
- Embedded Systems are becoming more and more distributed and networked;
- They are comprised of many co-operating individual components.
Examples of such systems are networks of sensors and actuators, home and car
networks, communication networks, distributed radio telescopes, personal health
care networks, environmental monitoring networks, ubiquitous and pervasive
computing networks, and more.
There are several fundamental problems that make the design of Distributed
Embedded Systems and Software difficult:
- Handling non-functional and resource constraints,
- Design under conflicting dependability criteria,
- Trade-off between average performance and predictability.
To master these problems, it has been found that conventional computer science
and engineering methods are at their limits. In fact, moving from traditional
component-level design to multi-component distributed systems demands for a
paradigm shift in both modelling and design methods. The workshop will address
specific challenges in this emerging paradigm shift. They are
- Modular design strategies for distributed embedded systems (composable
analysis methods; rich component concepts, design methodologies),
- Predictability and Efficiency (exploitation of the trade-off; approaches to
predictability vs. efficiency from hardware platforms to software systems)
- Design Space Exploration and Application Scenarios (applications in
- automotive, sensor and actuator networks, mechatronics; multi-objective
- optimization and bio-inspired exploration methods)
To promote a convergent way of interaction, the first two days of the workshop
will be devoted to talks and discussions, ordered according to the 4 topics given
above. The remaining two days will have a true workshops format to actually
going ahead dealing with performance analysis, focusing on benchmark
problems, and classication and comparison of proposed and available methods.
In particular, a set of benchmark examples will be defined and existing methods
such as real-time calculus, holistic methods, Symta/S, timed automata will be
compared.
The workshop is supported by (a) the Lorentz Center at Leiden University and (b)
the honorary Pascal Chair of Leiden University and (c) the European Network
of Excellence ARTIST2.
