A Sensitivity Analysis of Multi-objective Cooperative Planning Optimization Using NSGA-II

The Non-dominated Sorting Algorithm II (NSGA-II) is one of the most popular genetic algorithms (GA). It is characterized with a high optimization quality that is demonstrated for several multi-objective problems in various disciplines. During the optimization, several genetic parameters are involved and influence the solution quality. The purpose of this paper is to investigate the influence of the NSGA-II parameters on the optimization process, while solving a multi-objective planning model. Two cases, having opposite demand topology, are studied. Results show a considerable impact of NSGA-II parameters, especially the population size and the mutation operators, on the algorithm behaviour and the optimization process. This investigation offers to the partners several optimal production plans with different parameters combinations, and allows them to select the most influential parameter that provide several good solutions.