This work develops the approach and presents the results of a new model for applying intelligent agents to complex distributed interactive simulation for command and control. In the framework of tactical command, control communications, computers and intelligence (C₄I), software agents provide a novel approach for efficient decision support and distributed interactive mission training. An agent-based architecture for decision support is designed, implemented and is applied in a distributed interactive simulation to significantly enhance the command and control training during simulated exercises. The architecture is based on monitoring, evaluation, and advice agents, which cooperate to provide alternatives to the dec ision-maker in a time and resource constrained environment. The architecture is implemented and tested within the context of an AWACS Weapons Director trainer tool.

The foundation of the work required a wide range of preliminary research topics to be covered, including real-time systems, resource allocation, agent-based computing, decision support systems, and distributed interactive simulations. The major contribution of our work is the construction of a multi-agent architecture and its application to an operational decision support system for command and control interactive simulation. The architectural design for the multi-agent system was drafted in the first stage of the work. In the next stage rules of engagement, objective and cost functions were determined in the AWACS (Airforce command and control) decision support domain. Finally, the multi-agent architecture was implemented and evaluated inside a distributed interactive simulation test-bed for AWACS Vv'Ds. The evaluation process combined individual and team use of the decision support system to improve the performance results of WD trainees.

The decision support system is designed and implemented a distributed architecture for performance-oriented management of software agents. The approach provides new agent interaction protocols and utilizes agent performance monitoring and remote synchronization mechanisms. This multi-agent architecture enables direct and indirect agent communication as well as dynamic hierarchical agent coordination. Inter-agent communications use predefined interfaces, protocols, and open channels with specified ontology and semantics. Services can be requested and responses with results received over such communication modes. Both traditional (functional) parameters and nonfunctional (e.g. QoS, deadline, etc.) requirements and captured in service requests.