Traditional inventory models only involve single objective that relates to several cost items or service requirements. Even in its multi-objective formulation, most models have been solved with traditional optimization techniques by combining several objectives into a single one. The solutions obtained are unsatisfactory because their non-dominance is not guaranteed. This paper incorporates a local search and clustering mechanism into the multi-objective particle swarm optimization (MOPSO) algorithm to solve two bi-objective inventory planning models, both having a cost minimization objective along with the stockout occasions minimization objective (named as N-model) and the number of items stocked out minimization objective (named as B-model), respectively. The way of multiobjective analysis can determine the non-dominated solutions of order size and safety factor simultaneously. We compare the set coverage metric of both non-dominated solution sets by their expected relevant cost and the service level per order cycle. Our results show that even under the service level measure favorable to the N-model, the non-dominated solution set of the B-model are closer to the Pareto-optimal front than that of the N-model.