Analysis Of Evolutionary Algorithms Based On Different Noise

Estimation of Distribution Algorithms(EDAs) is a new kind Evolutionary Algorithms in the calculation domain. It is a combination of statistical learning theory and stochastic optimized algorithms. EDAs does not have the traditional evolutionary operators, but use the probability model to describe the distribution of candidate solutions, then sample according to the probability model, produces the new population, carries on repeatedly to realizes population's evolution. UMDA is the most basic element of EDA with irrelevant variables . Therefore, combined with the Inherent random of Evolutionary process , this article bring up Stochastic UMDA algorithm, and in connection with this algorithm, seek out potential function. On the basis, this article Discuss the effects of different noise on potential function. By numerical results, noise can change the potential plane and thereby changing the algorithm convergence ,so it provide reference for the design of the algorithm.