基于基因水平多样性的微种群教与学优化算法.

The performance of micro-population teaching-learning-based optimization(TLBO) algorithm is mainly depended on the population diversity. In order to further improve its performance, this paper proposed a micro-population teaching-learningbased optimization based on gene level diversity(MTLBO-GLD) . In the proposed algorithm, the pop ulation diversity was monitored at the genetic level, and the chaos search and the cosine function were used to improve the population diversity in different evolutionary stages. The proposed algorithm was compared with eight meta-heuristic algorithms ( including four micro-population algorithms and four non-micro-population algorithms) on 13 test functions . The experimental results show that the overall performance of the MTLBO-GLD is significantly better than that of compared algorithms. [ABSTRACT FROM AUTHOR]