Adaptive Ant Colony Optimization with Several Pheromone Updates for Constraint Satisfaction Problems

Abstract

Ant colony optimization, ACO, has been applied to solving constraint satisfaction problems, CSPs., as an effective meta-heuristics. Because most of ACO based algorithms have prepared only the single pheromone update method, however, such algorithms have sometimes been inefficient for CSP instances very hard to solve due to dependence on how pheromone accumulates. In this paper, we propose an ACO based algorithm that can deal with several pheromone update methods. Besides, the proposed method also prepare an adaptive mechanism, in which pheromone update methods suitable to each problem instance to be solved can dynamically be adjusted during the search process. We also demonstrate that the proposed method can be more effective than some ACO based algorithms with the single pheromone update method for large-scale and very hard instances of the graph coloring problem that has been known as one of typical examples of CSPs.