Estimating Differential Evolution crossover parameter with VNS approach for continuous global optimization

There are two metaheuristics that deserve considerable attention in the past years by both academics and practitioners. VNS (Variable Neighborhood Search) is a unique and effective concept of combinatorial and global metaheuristic, based on the principles of systematic changes in the environment in conjunction with local searches. On the other side, Differential Evolution (DE), which presents a simple concept of the global search space based on evolutionary algorithm that is used in many practical applications. In this paper we use VNS idea to estimate crossover parameter, the important parameter of DE heuristic. For that purpose we propose a family of distributions for controlling distances in the search space.