Chaotic parallel genetic algorithm with feedback mechanism and its application in complex constrained problem

Lots of improvements have been made to genetic algorithm, but they did not nearly solve the dilemmas - slow convergence and crowding problem due to the conventional genetic algorithms´ oversimplified mechanisms: pseudo-diversity of population and randomized evolutionary operation. Basing on a new scheme -random evolution plus feedback, which is reported to well represent the nature of biological evolution process, we propose chaotic parallel genetic algorithm with feedback mechanism. In this new algorithm, chaotic mapping is embedded for maintaining a good diversity of population; and Baldwin effect based posterior reinforcement learning, which can successfully deal with the feedback information from evolutionary system, is included to speed up the evolution along the right direction. The performance of this new algorithm was demonstrated on two well-known benchmark constrained problems. Results show that this new genetic algorithm is feasible and quite effective.