A two-stage preference-based evolutionary multi-objective approach for capability planning problems

As a type of long-term planning problems, capability planning problems (CPPs) have received considerable attention in the defense and military area. In this paper, we model CPPs as a type of project scheduling problems, referred to as multi-mode resource investment project scheduling problems (MRIPSPs). The makespan and the cost are simultaneously considered. To deliver decision support, a two-stage approach is developed considering both operational and strategic perspectives. At both levels, knowledge of experts or preference of decision makers is utilized. By integrating domain knowledge at the operational level and preference information at the strategic level into the optimization algorithm, a two-stage preference-based multi-objective evolutionary algorithm is proposed. A hypothetical case with 16 tasks is studied. The experimental results show that by focusing computational efforts on the sub-regions where experts or decision makers are interested, we can obtain the solutions which are not only closer to the true Pareto front in objective space, but also hold good characteristics in decision space.

► We model capability planning problem as multi-objective project scheduling problem.
► We propose a two-stage preference-based MOEA for the CPP.
► Domain knowledge and preference information are incorporated into MOEA.
► Preferred Pareto-optimal solutions with good characteristics can be obtained.