Modified bat algorithm based on covariance adaptive evolution for global optimization problems

Bat algorithm is a newly proposed swarm intelligence algorithm inspired by the echolocation behavior of bats, which has been successfully used in many optimization problems. However, due to its poor exploration ability, it still suffers from problems such as premature convergence and local optimum. In order to enhance the search ability of the algorithm, we propose an improved bat algorithm, which is based on the covariance adaptive evolution process. The information included in the covariance adaptive evolution diversifies the search directions and sampling distributions of the population, which is of great benefit to the search process. The proposed approaches have been tested on a set of benchmark functions. Experimental results indicate that the proposed algorithm obtains superior performance over the majority of the test problems.