Biogeography-Based optimization (BBO) is a nature inspired optimization technique that has excellent exploitation ability but the exploration ability needs to be improved to make it more robust. With this objective in mind, Garg and Deep proposed Laplacian BBO (LX-BBO) based on the Laplace Crossover which is a Real Coded Genetic Crossover Operator. It was concluded that LX- BBO outperforms its competitors. A natural question is to incorporate real coded mutation strategies into LX-BBO in order to improve its diversity. Therefore, in this paper, the exploring ability of LX-BBO is further investigated by using six different types of mutation operators present in literature. Gaussian, Cauchy, Levy, Power, Polynomial and Random mutation are used to test which mutation works best for LX-BBO. The performance of all these versions of BBO are measured on the benchmark problem set proposed in CEC 2014. On the basis of the criteria lay down by CEC, analysis of numerical and graphical results and statistical tests it is concluded that LX-BBO works best with Random and Cauchy Mutation.
An Empirical Study on the Scalability of Selective Mutation Testing