| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 599.35 KB | Adobe PDF |
Advisor(s)
Abstract(s)
In heterogeneous environments, diversity of resources among the devices
may affect their ability to perform services with specific QoS constraints,
and drive peers to group themselves in a coalition for cooperative service
execution. The dynamic selection of peers should be influenced
by user’s QoS requirements as well as local computation availability,
tailoring provided service to user’s specific needs. However, complex
dynamic real-time scenarios may prevent the possibility of computing
optimal service configurations before execution. An iterative refinement
approach with the ability to trade off deliberation time for the quality
of the solution is proposed. We state the importance of quickly finding
a good initial solution and propose heuristic evaluation functions that
optimise the rate at which the quality of the current solution improves
as the algorithms have more time to run.
Description
Keywords
Citation
Publisher
Springer