采用多项式变异策略和分解方法的多目标进化算法

Multi-objective evolutionary algorithm using decomposition method and polynomial mutation operator

MOEA/D-M2M算法将一个多目标优化问题同时转换为若干个多目标优化子问题,分别求得这些子问题的Pareto解,最终得到原多目标优化问题的Pareto解,保证了种群的多样性,比MOEA/D具有更好的算法性能.多项式变异算子具有强化局部搜索和加强收敛的作用,但是在多目标进化算法中应用多项式变异算子的成果不多.将多项式变异算子和MOEA/D-M2M中提出的多目标优化问题的新的分解方法相结合,提出了一种新的采用多项式变异策略和分解方法的多目标进化算法(MOEA/PmD).考虑到非均匀变异算子通过动态调整步长获得自适应性的特点,尝试通过将非均匀变异算子替换MOEA/PmD中的多项式变异算子而构造采用非均匀变异算子和分解方法的多目标进化算法(MOEA/NumD).实验表明MOEA/PmD算法比MOEA/NumD算法和MOEA/D-M2M算法具有更好的性能.

The algorithm ofMOEA/D-M2M can transform multi-objective optimization problem into a number of multi-objective optimization sub-problems and obtains the Pareto solutions of these sub-problems separately,and finally obtains the Pareto solution of the multi-objective optimization problem,which ensures the diversity of population and has better algorithm performance than MOEA/D.Polynomialmutation operator has the function of strengthening local search and convergence,but there is less work on the application of themutation operator in the multi-objective evolutionary algorithm.A new multi-objective evolution algorithm using decomposition methods and polynomial mutation operators(MOEA/PmD)is proposedby combining the polynomial mutation operator and the new decomposition method of multi-objective optimization problem proposed in MOEA/D-M2 M.Non-uniform mutation operator obtains the adaptability by dynamically adjusting the step size,an attempt is done to replace the polynomial mutation operator in MOEA/PmD with the non-uniform mutation operator,and multi-objectiveevolutionary algorithm using non-uniform mutation operator and decomposition method(MOEA/NumD)is devised.Experiments show MOEA/PmD algorithmhas better performance than MOEA/NumD and MOEA/D-M2M.