Hybridizing cuckoo search algorithm with bat algorithm for global numerical optimization

The cuckoo search algorithm (CSA) is a promising metaheuristic algorithm for solving numerous problems in different fields. It adopts the Levy flight to guide the search process. Nonetheless, CSA has drawbacks, such as the utilization of global search; in certain cases, this technique may surround local optima. Moreover, the results cannot be guaranteed if the step size is considerably large, thereby leading to a slow convergence rate. In this study, we introduce a new method for improving the search capability of CSA by combining it with the bat algorithm (BA) to solve numerical optimization problems. The proposed algorithm, called CSBA, begins by establishing the population of host nests in standard CSA and then obtains a solution through particular part to identify a new solution in BA (i.e., further exploitation). Therefore, CSBA overcomes the slow convergence of the standard CSA and avoids being trapped in local optima. The performance of CSBA is validated by applying it on a set of benchmark functions that are divided into unimodal and multimodal functions. Results indicate that CSBA performs better than the standard CSA and existing methods in the literature, particularly in terms of local search functions.