Boundary conditions in Tree-Seed Algorithm: Analysis of the success of search space limitation techniques in Tree-Seed Algorithm

Abstract

Swarm intelligence or evolutionary computation algorithms search possible solutions in a predetermined search space of an optimization problem. In some cases candidate solutions go out of search space during the search. In such situations, search space limitation techniques or boundary conditions are used for sway up this outcast individual into search space. The boundary conditions are classified two main categories whose names are restricted and unrestricted techniques. Restricted boundary conditions forces outcast individual into search space but unrestricted boundary conditions does not force. In this work we use four restricted boundary conditions whose names are Absorbing, Reflecting, Damping and Randomly. Additionally, three unrestricted boundary conditions (Invisible, Invisible Reflecting and Invisible Damping) are used in the study. These boundary conditions are applied in Tree-Seed Algorithm (TSA). The test material is five standard benchmark functions and these are Sphere, Rastrigin, Rosenbrock, Griewank and Ackley. The main idea of this study is to investigate whether there is a significant difference among the limitation methods in TSA. Experimental results show that there is no significant difference among the boundary conditions methods for TSA.