含区间参数多目标系统的微粒群优化算法

Particle Swarm Optimization for Multi-objective Systems with Interval Parameters

参数不确定优化问题是实践中经常遇到的复杂优化问题,现有方法多针对单目标函数的情况.本文利用微粒群优化算法解决含区间参数多目标优化问题,提出一种基于概率支配的多目标微粒群优化算法.该算法通过定义概率支配关系,比较所得解的优劣;基于σ区间值,选择微粒的全局极值点,并给出新的微粒个体极值点及外部储备集的更新策略.与传统多目标微粒群优化算法比较,仿真结果表明本文所提算法的有效性.

Optimization problems with uncertainties are a kind of familiar and complicated optimization problems, and most of the existing methods only deal with the case of a single-objective function. To solve multi-objective optimization problems with interval parameters by particle swarm optimization, a multi-objective particle swarm optimization algorithm based on probable dominance is proposed in this paper. In the algorithm, the probable dominance and the a intervals are presented to compare the quality of solutions and select the globally optimal particles, respectively. A novel strategy for updating locally optimal particles and exterior archive are put forward. The feasibility of the proposed algorithm is validated by simulation results.