Applied Cloning Techniques for a Genetic Algorithm Used in Evolvable Hardware Design

摘要

Genetic algorithms are commonly used to perform searches on complex search spaces for optimum solutions of many real-world problems. The evolvable hardware domain presents many problems with complex search spaces subject to the use of a genetic algorithm as an optimization technique for field programmable gate arrays (FPGA) implementations. The optimization of FPGA implementations, in general, are naturally difficult problems to solve using conventional genetic algorithm techniques due to the large number of local optima points. Therefore, an alternative cloning strategy is proposed which introduces a more powerful and diverse selection method taken directly from artificial biological principles. Performance studies of the new method provides good insight on the application of cloning to this domain.