Discrete Particle Swarm Optimization with Chaotic Initialization

摘要

A discrete particle swarm algorithm with chaotic initialization (DPSO-CI) is proposed for solving the combinational optimization problems, such as knapsack. The presented algorithm mainly employs the chaotic idea and pheromone mechanism used by ant colony algorithm. There are two reasons for using the ideas. To start with, the information existing in populations can be fully shared. Further, the initial solutions will not be gathered due to using chaotic method. At a matter of fact, swarm information can be more sufficiently shared by each particle. The performance of the proposed algorithm is evaluated in comparison with other heuristic algorithms. Our computational simulations reveal very encouraging results in terms of the quality of solution found.