SBIR-STTR Award

Stottler Henke proposes DREAMS, the Delay/disruption tolerant REinforcement learning and Aurora based coMmunication System, to address NASA’s need for distributed autonomous adaptive network communications technology, including planning and scheduling. DREAMS-equipped devices will sense and receive data and utilize the latest advances in Reinforcement Learning to discover optimal link parameters (e.g., frequency, modulation scheme) to improve various metrics (focusing on maximizing throughput and minimizing BER). The best links are combined to form potential communications paths from a start node to an end node. When feasible, these paths are aggregated by a nearby scheduling node which consolidates the network state and then allocates communications through the network. The proposed work builds on a series of our relevant research efforts (including several NASA-funded efforts) involving resource planning and scheduling, machine learning, low-SWaP algorithms, and distributed algorithms. We have already built a graphical satellite communications simulator which uses NASA’s WorldWind to display satellites and shifting communications links. In addition, we have already integrated our core planning and scheduling algorithm into NASA’s core Flight System. For these reasons, we propose aggressive Phase I objectives culminating in a Phase I Prototype of TRL 4. Potential NASA Applications (Limit 1500 characters, approximately 150 words): Distributed autonomous network communication optimization will become increasingly important as our activity and ambitions in space increase. Optimizing network communications by hand is becoming increasingly challenging; there is a clear need for machine-to-machine fully autonomous network optimization. Stottler Henke’s proposed technology can uniquely fulfill this gap, leveraging past successes with intelligent scheduling, machine learning, and distributed algorithms. Potential Non-NASA Applications (Limit 1500 characters, approximately 150 words): A clear transition opportunity is communications for military operations to coordinate mobile and stationary assets in real time in potentially denied environments. Improving situational awareness by increasing data flow in adversarial environments will significantly improve mission outcomes. Commercial networks with intermittent/variable links (including commercial space networks) could benefit. Duration: 6

Cognitive communication techniques are needed to ensure optimal use of very expensive space communications resources. The vast distances and numerous satellites in current and future NASA missions necessitate multi-hop communications utilizing temporary stores. Space communication networks are characterized by intermittent links, high latencies, low bandwidths, ad hoc connections, mobile physical nodes, asymmetric data rates, higher error rates, and heterogenous node types. DREAMS focuses on two separate but related aspects of optimal communications—routing and link optimization. Link optimization is the ability to optimize a given link by tuning the modulation scheme, coding scheme, transmit power, symbol rate, and roll-off factor, where optimality is the weighted sum of Bit Error Rate (BER), throughput, occupied bandwidth, spectral efficiency, transmit power efficiency, and Direct Current (DC) power consumption. Routing refers to the ability, given that links are already optimized and known (to the extent possible), to optimally schedule storage and transmission of data to maximize throughput. To optimally fill the router role, in Phase II we will develop a near-operational, distributed, optimized transmission and storage scheduler in three versions integrated with GRC’s ground testbed and ready for thorough testing in realistic simulations on a large number of very diverse scenarios. The distributed nature is accomplished by a straightforward division of labor between separate computational nodes and exchange of extremely low volume information (resource status and the current schedule). The Link Optimizer is based on Machine Learning techniques using data from KRATOS’s high fidelity RF Link simulator while the scheduler is based on the bottleneck avoidance algorithm, which uses information from the entire schedule and current resource status and congestion to best utilize ALL possible links to maximize successful transmission of the highest number of packets. Potential NASA Applications (Limit 1500 characters, approximately 150 words): DREAMS will be directly useful for any kind of spacecraft-based communication, whether it be commanding and health and status telemetry; audio, video, or other SATCOM traffic; or Internet Data packets. The most direct targets for commercialization of this technology are NASA’s LunaNet, Space Communication and Navigation (SCaN) program (which includes the Near Earth Network, Space Network, and Deep Space Network), and other NASA space communication applications. Potential Non-NASA Applications (Limit 1500 characters, approximately 150 words): The DoD has similar requirements and Stottler Henke is already involved in several applicable programs including scheduling on the Space Force’s Satellite Control Network (SCN), including the SCN’s userbase which includes DoD SATCOM satellites, and the Evolved Strategic SATCOM program, making them probable avenues of transition. Commercial SATCOM and satellite-based Internet are also targets. Duration: 24