NL-SOMA-CLP for real parameter single objective bound constrained optimization

Hao Ding, Yongfeng Gu, Hua Wu, Jun Zhou

Abstract: This paper presents a competition entry for the Real Parameter Single Objective Bound Constrained Optimization at The Genetic Evolutionary Computation Conference (GECCO) 2022. A new variant of Self-organizing Migrating Algorithm with CLustering-aided migration and adaptive perturbation vector control (SOMA-CLP) is proposed in this paper, which is titled Non-Linear Population Size Reduction and Nearest Neighbor Leader Selection SOMA-CLP(NL-SOMA-CLP). Overall, NL-SOMA-CLP improves the SOMA-CLP by using two techniques: a) a non-linear automatic reduction of population size and b) a nearest neighbor leader selection strategy.