Intelligent hybrid cuckoo search and β-hill climbing algorithm

Abstract

One of the major problems that is usually associated with any optimization algorithm including the Cuckoo Search (CS) algorithm is the premature convergence to suboptimal solutions. This problem normally occurs when the optimization operators of CS are not able to maintain the diversity of the solutions over multiple generations. One possible solution to the problem of premature convergence of CS is to hybridize it with other search techniques to reduce the likelihood of premature convergence. However, the hybrid CS algorithms normally require more computations than the original CS algorithm. The β-hill climbing algorithm, a variation of the Hill climbing algorithm, is capable of reaching better solutions in a shorter time than many popular local search algorithms. This paper proposes a new hybrid CS algorithm (CSBHC) that intelligently combines the CS algorithm with the β-hill climbing algorithm. In order to balance between the computational time and effectiveness of CSBHC, the β-hill climbing algorithm is called at each iteration of CSBHC based on an exponentially decreasing probability (i.e., the probability function used in Simulated Annealing). The proposed algorithm was evaluated and compared to popular hybrid CS algorithms using 16 standard benchmark functions. The experimental results suggest that the proposed algorithm produces more accurate results in a shorter running time compared to the original CS and other approaches. 2010 MSC: 00-01, 99-00, Keywords: Cuckoo search, β-Hill climbing search, Simulated annealing, Optimization, Metaheuristic