A Multi-population QUasi-Affine TRansformation Evolution Algorithm for Global Optimization

Abstract

In this paper, we propose a new Multi-Population QUasi-Affine TRansformation Evolution (MP-QUATRE) algorithm for global optimization. The proposed MP-QUATRE algorithm divides the population into three sub-populations with a sort strategy to maintain population diversities, and each sub-population adopts a different mutation scheme to make a good balance between exploration and exploitation capability. In the experiments, we compare the proposed algorithm with DE algorithm and QUATRE algorithm on CEC2013 test suite for real-parameter optimization. The experimental results indicate that the proposed MP-QUATRE algorithm has a better performance than the competing algorithms.