Improving Bat Algorithm Using Clustering

Bat algorithm (BA) is a new and promising metaheuristic search algorithm which could outperform existing algorithms. However, BA can be easily trapped in a local optimum regarded to low exploration ability. The present study proposed a new heuristic to escape such scenario. The proposed algorithm uses a clustering-based hybridization method which detects the early convergence of BA population by analyzing similarities among individuals. This algorithm is evaluated on CEC۲۰۱۷ benchmark suite. The Experiments demonstrate that the algorithm achieves better results than variants of BA in every way

کلیدواژه ها:

Bat Algorithm ، Metaheuristic search ، Nature inspired search ، Clustering