earticle

영어

In allusion to the shortcomings of easy falling into the local optimization and difficult obtaining Pareto optimal solutions for the original ant colony optimization algorithm in solving the complex optimization problems, multi-population, parallel mechanism, dynamic evaporation strategy and chaos theory are introduced into the original ant colony optimization algorithm in order to propose an improved multi-population ant colony optimization(MPPDCACO) algorithm in this paper. In the proposed MPPDCACO algorithm, the ant colony is divided into scout ants, search ants and worker ants in order to make the ACO algorithm as far as possible to avoid falling into local optimization and improve the local search ability of ant colony. The multi-population parallel mechanism is used to exchange the information and improve the computational effectiveness. The dynamic evaporation strategy is used to dynamically adjust the evaporation coefficient of pheromone in order to improve the global search capability of the ACO algorithm. The chaos theory is used to realize the optimization search in order to obtain the pheromone distributing in choosing path process. So the proposed MPPDCACO algorithm can prevent the local convergence caused by the misbalance of pheromone and can improve the searching ability. In order to test the optimization performance of the proposed MPPDCACO algorithm, 6 traveling salesman problems are selected from the TSPLIB in here. The experimental results show that the proposed MPPACACO algorithm takes on better global searching ability and higher convergence speed.