Fuzzy Logic Resource Management and Coevolutionary Game-based Optimization

Abstract

Abstract : A fuzzy logic expert system has been developed that automatically allocates electronic attack (EA) resources in real-time. This expertise-based resource manager is made up of four trees: the isolated platform tree, the multiplatform tree, the fuzzy parameter selection tree, and the fuzzy strategy tree. The initial version of the algorithm was optimized using a genetic algorithm using fitness functions constructed based on expertise. A new approach is being explored that involves embedding the resource manager in an electronic game environment. The game allows a human expert to play against the resource manager in a simulated battle space with each of the defending platforms being exclusively directed by the fuzzy resource manager and the attacking platforms being controlled by the human expert or operating autonomously under their own logic. This approach automates the knowledge discovery problem. The theory of coevolutionary optimization is introduced, reoptimization criteria and stopping criteria are discussed, an algorithm for automatically constructing coevolutionary fitness functions is introduced, and examples are provided to show the effectiveness of coevolutionary optimization. A measure of effectiveness (MOE) for validation is discussed. Finally. the effectiveness of the resource manager and the optimization procedures is shown through a demanding example.