Applied Mathematics & Information Sciences

Author Country (or Countries)

P.R. China


Decomposition of multi-objective evolutionary algorithm has better distribution, but the number of groups will increase dramatically as the target number increases, seriously affecting the efficiency of the algorithm. This paper presents a decomposition of multi-objective evolutionary algorithm based on estimation of distribution, the basic idea of which is: to decompose multiple objectives into several single objective first and then to establish the probability model for every single objective based on the idea of estimation of distribution, generating the solution by sampling. Numerical analysis and experiments show that the solution of the new algorithm not only has better diversity and uniformity, but also the computational complexity of the algorithm is significantly lower than the decomposition of multi-objective evolutionary algorithm, especially for optimization of three goals.

Suggested Reviewers


Digital Object Identifier (DOI)