Finding effective courses of action using particle swarm optimization

The paper applies particle swarm optimization (PSO) technique to identify effective courses of action (COAs) in a dynamic uncertain situation. The uncertain situation is modeled using timed influence nets (TINs), an instance of Dynamic Bayesian Networks. The TIN-based framework aids a system analyst in connecting a set of actionable events and a set of desired effects through chains of cause and effect relationships. The purpose of building these TIN models is to analyze several courses of action (COAs) and identify the ones that maximize the likelihood of achieving the desired effect(s). The paper attempts to automate this identification process of the best COA. It does so by exploring the solution space, consisting of potential courses of action, using PSO. The paper also compares the performance of PSO with that of an evolutionary algorithm (EA). The results suggest there is not a significant difference between the performances of the two techniques but PSO takes less time compared to EA.