Adaptive Parallel Ant Colony Algorithm

An adaptive parallel ant colony optimization is presented by improving the critical factor influencing the performance of the parallel algorithm. We propose two different strategies for information exchange between processors: selection based on sorting and on difference, which make each processor choose another processor to communicate and update the pheromone adaptively. In order to increase the ability of search and avoid early convergence, we also propose a method of adjusting the time interval of information exchange adaptively according to the diversity of the solutions. These techniques are applied to the traveling salesman problem on the massive parallel processors (MPP) Dawn 2000. Experimental results show that our algorithm has high convergence speed, high speedup and efficiency.