Modelling of production process using multiple ant colony approach

Artificial intelligence systems are often used to model production processes. One of the most commonly used methods are the swarm algorithms. Currently, different types of biologically inspired optimization algorithms (swarm ones) have been proposed for solving optimization problems, such as: genetic algorithms, differential evolution algorithms, ant algorithms (Ant Colony Optimization), the particle swarm optimization algorithm, bee algorithm. Latelythe new version of the last algorithm has been developed called the artificial colony algorithm (ABC). It is used for numerical optimization, which involves simulating the behavior of a honeybee swarm. The ant algorithm was proposed by Marco Dorigo, It is a probabilistic technique of solving problems by searching for good roads in graphs. It is inspired by the behavior of ants looking for food for their colony. In the real world, ants move randomly; when they find food, they return to their colonies leaving a trace consisting of pheromones. When another ant encounters this trail, it stops moving randomly and follows a trace towards food. In this paper it is described the application of the multiple colony version (MAC) of the ant algorithm for logistics problems optimization in production system.