摘要： 为实现偏好与群体决策的结合应用，提出基于群体距离的多目标粒子群优化算法。通过调整解与参考点的群体距离引导粒子靠近偏好区域，运用格栅方法和改进的剪枝策略实现解在Pareto边界的均匀分布，求出与群体成员偏好相关的部分Pareto最优集，从而减少计算成本、加快收敛速度。实验结果表明，该算法得到的解更靠近真实Pareto前沿，且对不同个体决策成员都有效。

关键词: 群体决策, 群体距离, 参考点, 多目标粒子群优化

Abstract: In order to realize combined application of preference and group decision, this paper presents multi-object particle swarm optimization algorithm based on group distance. It leads the particle flying to the solution preference area by adjusting the group distance between particle and the solution reference point step by step, and applies grid strategy and improved pruning strategy to maintain the diversity of solution in Pareto boundary. The computing cost is reduced and the convergence rate is improved through a preferred and a smaller set of Pareto optimal solution is found. Experimental results show that the solutions fund by the algorithm is nearer the Pareto front and is effective to all decision members.

Key words: group decision, group distance, reference point, multi-object particle swarm optimization

中图分类号: 

• TP393