Multi-Objective Differential Evolution with Taguchi-based adjustable proportional distribution

Recently, Multi-Objective Differential Evolution (MODE), powerful and efficient population-based stochastic processing, has become an indispensable algorithm for solving numerical optimization problems widely. It is found in various benchmark functions that traditional MODE is unable to search global optima completely, falling into local optima because only using one strategy to search global optimal. This paper proposes adjustable proportional distribution (APD) mechanism to deal with this problem. The proposed APD-MODE can combine several strategies with proportional distribution to search global optima. It calculates proportions of each strategy in external archive and then uses Taguchi method to select the best proportion in evolution. In next iteration, it selects the best proportion to adjust particles size and scale factor F used in each strategy according to Taguchi method. Benchmark experiments prove that APD-MODE can improve the maximum spread of solutions in external archive and find global optima more effectively and completely.