An efficient hybrid swarm intelligence optimization algorithm for solving nonlinear systems and clustering problems

This article proposes a new hybrid swarm intelligence optimization algorithm called monarch butterfly optimization (MBO) algorithm with cuckoo search (CS) algorithm, named MBOCS, for optimization problems. MBO algorithm is known for its disability to discover feasible solutions over different runs because it may trap in the local minima. Also, CS is a recent powerful algorithm, while it may consume a large number of function evaluations to get the optimal solution, and this is one of the disadvantages of this algorithm. MBOCS can circumvent the disadvantages of MBO and CS algorithms. In this work, we integrate MBO with CS to improve the quality of solutions to solve various optimization problems, namely unconstraint benchmark functions, nonlinear systems and clustering problems. We solve fifteen of CEC’15 benchmark functions and compare our results with various algorithms such as group search algorithm, harmony search, particle swarm optimization and other hybrid algorithms in the literature. Moreover, we apply MBOCS on ten known nonlinear systems and eight real-world data from UCI. The results of MBOCS were compared with other known algorithms in the literature. The experimental results show that the proposed hybrid algorithm is a competitive and promising method for solving such optimization problems and outperforms other compared algorithms.