"Ant Colony Optimization"

by

Matteo Borrotti

University of Bologna; European Centre for Living Technology

In this work we introduce a new possible application in the area of Design of Experiments and Combinatorial Optimization. Combinatorial Optimization involves finding values for discrete variables so that the optimal solution in respect to a given objective function is found. Many optimization problems of practical and theoretical importance are of combinatorial nature.
One possible technique is to intelligently navigate the search space of the problem using a new algorithm inspired by the behaviour of social insect societies, the Ant Colony Optimization (ACO) Algorithm introduced by Marco Dorigo in 1992.
Ant Colony Optimization is based on the behaviour of real ants and it is a probabilistic technique for solving computational problems which can be reduced to finding good paths through graphs.  The idea behind ant algorithms is to use a form of artificial stigmergy to coordinate societies of artificial agents. Stigmergy is a form of indirect communication between ants mediated by modification of the environment.
Starting from ACO we decided to adapt this algorithm for Combinatorial Design of Experiments (DoE) to avoid some problems like llittle prior knowledge, highly nonlinear effects and complex response surfaces.
Therefore the aim of this work is to introduce the idea and the main characteristics of a novel approach for Combinatorial DoE based on a modified version of ACO.