Scheduling Tasks for AFSCN Resources using MBO Autonomous Planning (STARMAP)

ABSTRACT: Scheduling Air Force Satellite Control Network (AFSCN) resources is a challenge because windows of visibility are limited between satellites and remote tracking stations on the ground, and there are more requests for access than available resources. Human scheduling at a centralized location is a difficult, time-consuming, and inefficient endeavor because pre-planned routine tasks need to be combined with emergent priority access requests in real-time. AFSCN schedulers need an intelligent, distributed, real-time planning and scheduling tool that uses spacecraft telemetry data and automatically allocates antennas based on complex optimization criteria for operation in a"lights out"environment that will reduce the burden on human schedulers and enable them to focus on higher level objectives. Charles River Analytics proposes to design and demonstrate the feasibility of a framework for Scheduling Tasks for AFSCN Resources using MBO Autonomous Planning (STARMAP). STARMAP is an intelligent real-time planning and scheduling framework for distributed market-based optimization (MBO) of antenna resources to improve scheduling effectiveness of satellite networks. Our approach involves first defining and analyzing requirements, then designing a cooperative monitoring framework, developing a market-based task assignment algorithm, developing a limited-scope prototype, and formally evaluating the framework to demonstrate its effectiveness.TBA BENEFIT: We anticipate STARMAP will have immediate benefit to the AFSCN enterprise by enabling intelligent distributed contact request scheduling to improve scheduling effectiveness of satellite networks, and enable decreased staffing by AFSCN schedulers. STARMAP technology will also be incorporated into our AgentWorks commercial product by expanding it to include distributed market optimization agents, providing adaptive display capabilities, and expanding its computational reasoning abilities.