一种离散型多目标粒子群优化算法

为获得更好的非劣前端，提出一种离散型多目标粒子群优化算法。该算法根据离散型多目标优化问题的特点，将种群分成多个子种群，在各个子种群中利用表现型共享的适应度函数选择每个子种群的最优粒子。通过多个最优粒子的引导，使整个种群分布更均匀，避免陷入局部最优，保证了解的多样性。实验表明了该算法的有效性。

A Discrete Multi-objective Particle Swarm Optimization Algorithm

To obtain a better approximation of true Pareto front, a discrete multi-objective particle swarm optimization （PSO） algorithm is proposed in this paper. According to the features of discrete multi-objective optimizaion problem （MOP）, an evolutionary swarm is divided into several subswarms and a fitness function based on phenotype sharing is introduced to select the optimal particle for each subswarm. By the guidance of multiple optimal particles, the whole particle swarm is distributed uniformly and avoided local optima, and the diversity of the solution can be ensured. The experiments show the effectiveness of the presented algorithm.