An Improved Estimation of Distribution Algorithm Based on the Entropy Increment Theorem

Abstract

To systematically harmonize the conflict between selective pressure and population diversity in estimation of distribution algorithms, an improved estimation of distribution algorithms based on the entropy increment theorem (IEDAEI) is proposed in this paper. IEDAEI conforms to the entropy increment theorem in simulating the competitive mechanism between energy and entropy in annealing process, in which population diversity is measured by the entropy increment theorem. By solving some typical high-dimension problems with multiple local optimizations, satisfactory results are achieved. The results show that this algorithm has preferable capability to avoid the premature convergence effectively and reduce the cost in search to some extent.