Using Cognitive Communications to Increase the Operational Value of Collaborative Networks of Satellites

Abstract

Distributed satellite constellations utilizing networks of small satellites will be a key enabler of new observing strategies in the next generation of NASA missions. Small satellite instruments are becoming more capable, but are still resource constrained (i.e. power, data, scanning systems, etc.) in many situations. On a system scale, the primary purpose of collaborative communication among small satellites is to achieve system-level adaptivity. Collaborative communications however may also dramatically increase the complexity of the control algorithms for small satellite communication networks. Application of cognitive communication methods is one promising method to address this problem. In this paper, we discuss our recent investigations into how machine learning (ML) algorithms can be utilized in the high-level decision making of a communication system in a distributed satellite mission. We performed simulation studies to explore how the perception-action cycle could be applied to a collaborative small-satellite networks. To support this, we are using a recently developed open-source C++ library for the simulation of autonomous and collaborative networks of adaptive sensors.