Earticle

Ant colony algorithm (ACA) is a new heuristic algorithm which has been proven a successful technique and applied to a number of combinatorial optimization problems. An Granular ACA algorithm based on scout characteristic is proposed for solving the stagnation behavior and premature convergence problem of the basic ACA algorithm on TSP. Proposesing a Granular computing adaptive ant pheromones mechanism base on researching on ant colony algorithm model, pheromones update and pheromones selection had been improved. Make up the traditional ant colony algorithm for the calculation of distribution network planning that is slow and easy to fall into local optimal solution. And improved the convergence of the optimal solution. The validity of the GACA has been verified using a testing function. In addition, a satisfactory optimum solution for a Power Distribution Network Planning that has 73 users has been obtained.