Automating Satellite Operations Centers through Intelligent Request Generation and Deconfliction

ABSTRACT: The goal of this proposed effort is to develop intelligent automation that can improve the Air Force"s process of scheduling contacts between Satellite Operations Centers (SOCs) on the ground and satellites in orbit. The current process for selecting supporting resources ("supports") is largely manual and can require substantial effort as conflicts are resolved both locally and then globally at the 22nd Space Operations Squadron (22 SOPS). This process is currently handled by crews operating 24/7 to manage satellite telemetry, tracking and commanding (TT & C). This SBIR effort is seeking to reduce the required manpower and eventually transition to"lights out"operation at the SOCs. Our system, called Synth, will improve efficiency by intelligently prioritizing the available supports and considering a wide range of constraints that are currently cross-checked manually. Additional improvements will be made by integrating with Stottler Henke"s MIDAS, an intelligent scheduling agent that deconflicts schedule requests across all SOCs. Synth will transmit additional information for more general scheduling rules such that MIDAS can automatically adapt the global schedule without always needing to wait for approval from each SOC. Phase I proved the concept and has set the stage for full implementation of Synth in Phase II. BENEFIT: The most direct target for the results of this effort is, of course, providing intelligent automation for the Air Force Satellite Control Network (AFSCN) and more specifically SOCs. By Stottler Henke both demonstrating significantly improved performance during Phase II and ensuring that the ultimate results can be integrated into the operational scheduling systems with the proposed Synth system, the Air Force will have a strong incentive to operationalize the Phase II development of the proposed system. Beyond the Air Force, there is strong commercialization potential for this technology with NASA and private sector satellite operators. Additionally, there are many similarities between communication scheduling and sensor scheduling. Thus the algorithms developed here could be marketed to our existing Air Force and Navy sensor customers interested in sensor scheduling and coordination. Finally, there are the commercial applications for the technology developed for the Scheduler. We are already marketing Aurora, our general intelligent planning and scheduling framework, and we are customizing it for a variety of domains. The additional capabilities developed for communication scheduling can be synergistically marketed to the same clients. We anticipate that this effort will result in additional scheduling algorithms that we will be able to incorporate into our existing scheduling products, thus increasing the benefits they provide and their value.