Using Genetic Algorithms in Effects-Based Planning

In this paper, we propose a genetic algorithm-based method for evaluation of operational plans within effects-based planning. We formulate the effects-based planning problem as a bi-objective optimization problem, in which the distance from the initial state to the current state (g) and the distance from the current state to the desired end state (h) are minimized. To solve the problem, we adopt Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Considering an expeditionary operation scenario, we simulate a subset of possible plans and present the decision maker with a set of promising plans which are capable of approaching the desired end state efficiently. In order to discuss the efficiency and effectiveness of the algorithm, we compare the results of NSGA-II with the results of A*. The computational results show that NSGA-II is much more efficient than A* with regard to g. On the other hand A* is a little more effective with regard to h.