Multiple Topology SHADE with Tolerance-based Composite Framework for CEC2022 Single Objective Bound Constrained Numerical Optimization

Abstract

To further enhance the convergence performance and accuracy of SHADE, a SHADE with tolerance-based multiple topology selection framework (MTT_SHADE) is proposed in this paper. In MTT_SHADE, three population topologies are established employing the k-nearest neighbor network, small-world network, and random network, respectively, and the evolution of individuals depends on the neighborhoods derived from different topologies. The tolerance-based composite framework is proposed to select the appropriate topology for an individual at the same time. Specifically, local tolerance and global tolerance are predetermined, corresponding to the tolerance for individuals and the population, respectively. The topology involved in the evolution of the individual is replaced when the individual does not progress after successive iterations. The population that does not improve in effect after successive iterations are considered to have exceeded the global tolerance and the three population topologies are reconstructed. The CEC2022 competition on single objective bound-constrained numerical optimization and four state-of-the-art DE variants are employed to investigate the effectiveness of the proposed algorithm. Experimental results show that MTT_SHADE is competitive in terms of accuracy and convergence.