基于合作模型的协同免疫多目标优化算法

A Cooperative Immune Coevolutionary Algorithm for Multi-Objective Optimization

本文针对多目标优化问题Pareto最优解集合(PS)的分布特点,构造了一种基于新的子任务划分方法的合作型协同进化模型,并将该模型引入人工免疫系统中,提出了一种基于合作模型的协同免疫多目标优化算法(A Cooperative Immune Coevolutionary Algorithm for Multiobjective Optimization,CICAMO).CICAMO算法运用Tchebycheff分解方法进行子种群划分,然后对各个子种群建立线性概率统计模型分段逼近整个PS,在抗体繁殖上结合了克隆选择和模型采样两种方式.实验结果表明,CICAMO算法在求解质量和收敛速度上均表现良好,尤其对于决策变量非线性相关的多目标优化问题,性能尤为突出.

According to the distribution characteristics of the Pareto set （PS） of multi-objective optimization problems （MOPs）, a cooperative coevolutionary model with new problem decomposition method was designed. By introducing the proposed coevolutiunary model into artificial immune system, a cooperative immune coevolutionary algorithm for multi-objective optimization （CICAMO） was proposed.In CICAMO,the Tchebycheff decomposition method is employed to divide sub-populations at first, and then linear probabilistic models are built for each sub-population to piecewise approximate the distribution of the whole PS. In anti- body reproducing step, two types of approaches based on clonal selection and model sampling are employed. Experimental results in- dicate that CICAMO can achieve a good performance in terms of both solution quality and convergence rate, especially when solving MOPs with non-linear relationship between decision variables.