协同控制多目标粒子群算法研究

Research on Multi-Objective Particle Swarm Optimization with Cooperative Control

针对现有的多目标粒子群算法易陷入局部最优、难以平衡收敛性和多样性等方面的问题,提出一种协同控制多目标粒子群算法(CCMOPSO)。首先,算法脱离Pareto支配关系采用成就标量函数更新pbest。其次,提出了一种平均角度和最低距离相结合的协同策略,以删除外部存档中性能不好的非劣解。从而对存档进行维护,平衡收敛性和多样性,有利于非支配解逼近Pareto前沿。最后,将CCMOPSO算法与几个多目标优化算法在15个测试问题上进行仿真实验。实验结果分析表明CCMOPSO算法的有效性可以很好地平衡收敛性和多样性,避免陷入局部最优。从而说明CCMOPSO算法在处理多目标优化问题表现出较强的竞争力。

Aiming at the problems that existing multi-objective particle swarm optimization algorithms are easy to fall into local optima and difficult to balance convergence and diversity and so on,a multi-objective particle swarm optimization with cooperative control(CCMOPSO)is proposed.Firstly,the algorithmbreaks away fromPareto dominance relation and uses achievement scalarizing function to update pbest.Secondly,a cooperative strategy combining average angle and minimum distance is proposed to delete the non-dominated solutions with poor performance in the external archive,so as to maintain the archive,balance convergence and diversity,and help non-dominated solutions approach Pareto front.Finally,the CCMOPSO and several multi-objective optimization algorithms are simulated on fifteen test problems.The experimental results show the effectiveness of CCMOPSO,which can balance convergence and diversity well and avoid falling into local optima.It shows that CCMOPSOhas strong competitiveness in dealing with multi-objective optimization problems.