基于参考点和投票规则的多目标粒子群优化群体决策

MULTI-OBJECTIVE PARTICLE SWARM OPTIMIZATION FOR GROUP DECISION MAKING BASED ON REFERENCE POINTS AND VOTING RULES

针对巨量可选方案的群体决策问题,提出了一个新的基于参考点和投票规则的多目标粒子群优化算法。该算法把个体与参考点的支配关系或者距离作为一个重要因素,在选择引导者的锦标赛方法,局部最优更新规则,以及外部种群档案剪枝规则中都嵌入了基于支配关系或距离因素的投票规则,以找到群体决策解,并且提高搜索效率。仿真结果表明该算法有效。

In this paper,to solve the group decision making problem among massive options,the author present a new algorithm of multi-objective particle swarm optimization based on reference points.This algorithm takes the dominate relationship or distances between individuals and reference points as the important factor,and embeds voting rules which is based on dominate relationship or distances factor into tournament method for leader＇s selection,local best updating rule as well as pruning strategy of exterior population archives in order to find the solution of group decision making and to make the search more effective.Simulation results show that the proposed algorithm is effective.