A Novel Differential Evolution Algorithm with Adaptive of Population Topology

摘要

Differential evolution is a simple and efficient algorithm. Although it is well known that the population structure has an important influence on the behavior of EAs, there are a few works studying its effect in DE algorithms. In this paper, a novel adaptive population topology differential evolution algorithm (APTDE) is proposed for the unconstrained global optimization problem. The topologies adaptation automatically updates the population topology to appropriate topology to avoid premature convergence. This method utilizes the information of the population effectively and improves search efficiency. The set of 15 benchmark functions provided by CEC2005 is employed for experimental verification. Experimental results indicate that APTDE is effective and efficient. Results show that APTDE is better than, or at least comparable to, other DE algorithms.