Adaptive genetic algorithm based on cloud theory
Chaohua Dai · Control theory & applications · 2007
Traditional adaptive genetic algorithm(AGA)has higher convergence speed,but it still easily gets stuck at a local optimum.A novel algorithm called cloud-based adaptive genetic algorithm(CAGA)is introduced,which is based on cloud model with the properties of randomness and stable tendency.In the CAGA,the probabilities of crossover and mutation,p_c and p_m,are adaptively varied depending on X-conditional cloud generator.In X-conditional cloud generator, the average fitness of the current population is used as expected value Ex,and entropy En is specified based on the3Enrule of cloud model.CAGA can improve its convergence capacity because of the stable tendency of cloud model. Meanwhile,it can remarkably avoid a local minimum using the randomness of cloud model to maintain diversity in the population.Finally,the performance of the CAGA is compared with that of the standard GA(SGA) and AGA in optimizing several nontrivial multimodal functions with varying degrees of complexity.In all cases studied,CAGA is greatly superior to SGA and AGA in terms of robustness and efficiency.