Optimization of dynamic data types in embedded systems using DEVS/SOA-based modeling and simulation

New multimedia embedded applications are increasingly dynamic, and rely on Dynamically-allocated Data Types (DDTs) to store their data. The optimization of DDTs for each target embedded system is a time-consuming process due to the large searching space of possible DDTs implementations. This results in the minimization of embedded design variables (memory accesses, power consumption and memory usage). Till date some effective heuristic algorithms have been developed in order to solve this problem, however unreported, as the problem is NP-complete and cannot be fully explored. In these cases the use of parallel processing can be very useful because it allows not only to explore more solutions spending the same time but also to implement new algorithms. This research work provides a methodology to use Discrete Event Systems Specification (DEVS) to implement a parallel evolutionary algorithm within a Service Oriented Architecture (SOA), where parallelism improves the solutions found by the corresponding sequential algorithm. This algorithm provides better results when compared with other previously proposed procedures. In order to implement the parallelism the DEVS/SOA framework in utilized. Experimental results show how a novel parallel multi-objective genetic algorithm, which combines NSGA-II and SPEA2, allows designers to reach a larger number of solutions than previous approximations. This research also establishes DEVS/SOA as a platform for conducting complex distributed simulation experiments.