Self-adaptive bacterial foraging algorithm

Swarm optimization algorithms, considered in this paper, are based on the modeling of collective behavior in the colonies of living organisms - the ants, bacteria, bees, etc. The present work is devoted to the description of a new approach to building self-adaptive swarm optimization algorithms, with automatic adjustment of the algorithm parameters during its execution. The idea of constructing self-adaptive evolutionary algorithm is following - in the background of the main optimization algorithm we run auxiliary genetic algorithm, which purpose is the adjustment of the parameters of the basic algorithm, providing the maximum possible speed of convergence. The results of the numerical analysis of the self-adaptive version of bacterial foraging algorithm for standard test problems of continuous optimization are described.