Skip to Main Content
Self-adaptive evolutionary algorithms have gained more attention due to their flexibility to adapt to complex fitness landscape. We present a method to self-adapt crossover parameters of a genetic algorithm during evolution. Not only crossover type but crossover probabilities also are self-adapted allowing the search procedure to find out the most suitable parameters for each search phase. A new heuristic is proposed to improve crossover adaptation. The method has been evaluated on binary encoding and mixed encoding problems. Simulation results indicate the benefits of associating the proposed heuristic with additional flexibility resulting from the parameters adaptation in the crossover operation.