Constructive genetic algorithm with penalty function for a concurrent real-time optimization in embedded system design process

In this paper we present a genetic programming based constructive algorithm with penalty function for a concurrent real-time optimization in embedded system design process.Proposed approach uses genetic programming mechanism to optimize detecting and assignment of unexpected tasks process in embedded system design.Unlike others methodologies the approach described in this paper uses a penalty in objective function in optimization process.As a result during the evolution generations of individuals can also contain solutions which violate time constraints.Thus the approach is more proof to stop in local minima of optimizing parameters.Therefore the final result could be better adapted to the environment and the optimization process can be cheaper and more effective.