A Simulation-optimization Approach to Air Warfare Planning

Abstract

How can computer-aided planning systems deal with the complexities, uncertainties, and rapidly shifting information needed to support air warfare operational planning? This paper uses a hierarchical decomposition of decision-making, coupled to a predictive simulation model that estimates the probability distribution of the outcomes of candidate operational plans. The approach will generate, evaluate, and improve Blue plans while assuming that Red intelligently reallocates its forces, using stochastic optimization, to counter Blue's moves. Evaluation of each Blue plan is accomplished via a Stochastic Evaluator that draws multiple samples of potential outcomes and Red force levels for a given Blue force structure and combined target composition. The evaluation metric is the net discounted value from enemy targets hit. Linear programming heuristics and simulation generate Red's adaptively optimized responses, outcomes, and inferred relative marginal force values. The results of this two-player, multi-level simulation-optimization approach for operational planning and decision-making demonstrate that automated plan optimization and embedding of optimization algorithms into an operational planning cycle operating over a multi-period conflict can be made practical for current computers by hierarchical decomposition of planning and on-line decision and optimization problems into computationally practical tasks.