Bee Colony Optimization Analysis

Artificial Bee Colony (ABC) optimization was invented by Karaboga. ABC is a Swarm Intelligence approach which is being inspired from the foraging behaviour of real time honey bees. Bee Colony Optimization consists of three types of bees namely employed bees, onlooker bees and scout bees. ABC algorithm randomly generates initial population of bees P (I = 0) with their m food source locations throughout the iterations (I =1, 2…Imax) of searching processes of the three types of bees, where m denotes no of onlooker or employed bees which is equal to the food source locations. These food source positions are also called solutions that are having different amount of nectar which is known as the fitness function. Each solution i.e si (i=1, 2, 3,…m) is a d-dimensional vector, Where d is no of parameters of optimization.

Depending upon the visual information of the food source the employed bees updates the solutions in its memory and evaluates the nectar amount of the newly

The rate of recruitment measures the speed at which the artificial bees explore and exploits newly found feasible food locations. The overall performance of the ABC technique is dependent upon the prompt discovery and efficient utilization of the optimal food sources. In the same way; the effective solution of complex problems is also dependant upon the quick discovery of better solutions specially for the real time optimization problems in which both exploration and exploitation processes took place simultaneously. In Artificial Bee Colony, where exploitation process is performed by onlooker and employed bees in the search space, the scout bees manages the exploration of food resources. Detailed pseudo-code of the Artificial Bee Colony Optimization is given