SBIR-STTR Award

An innovative software-defined machine learning (ML)-powered network architecture will be developed to enable high performance within the globally distributed Synthetic Training Environment (STE), the High-Performance STE Overlay Network (HP-SON). Our HP-SON architecture utilizes software-defined networking (SDN) concepts combined with machine learning (ML) concepts to provide a virtualized overlay network architecture capable of autonomously learning network paths between distributed STE components and intelligently adapting to optimize user experience. Deep learning neural networks are utilized to learn and characterize network paths between STE components within the globally distributed STE network. HP-SON edge nodes use this learning to perform intelligent adaptation of network behavior and treatment of traffic based on network characteristics, user-driven policy, application behaviors and characteristics, and network loading conditions. Specifically, HP-SON implements dynamic application, performance, and traffic-aware 1) path selection, 2) protocol optimization, and 3) data compression, all enabled by recent advances in neural network ML and SDN techniques. The result is efficient usage of network resources and an improved overall user experience. While initially intended for application to the STE, HP-SON will be network agnostic. Consequently, this approach is believed to have wide commercial application to any IP network as a network performance acceleration appliance

The US Army is developing a sophisticated Synthetic Training Environment (STE), a federation of globally distributed training assets, which combines traditional live training exercises with virtual training environments, constructive training environments, and various Army gaming and simulator systems. In Phase II of this program, a functional prototype of a software-defined machine learning (ML)-powered network architecture, the High-Performance STE Overlay Network (HP-SON), will be built to optimize performance across this diverse network and deliver a usable STE training experience. In Phase I of this program, a limited prototype was developed to address the STE networking challenge, which resulted in a promising, yet nascent, Technology Readiness Level (TRL) 3 capability. The technical objective of this PHASE II effort is to fully implement the HP-SON system in the Phase I testbed and test the system and mature the capability to a TRL 5. The result will be a set of hardware and software that is ready to integrate into Army STE testbed facilities for testing in operationally relevant capabilities to increase its TRL to 6. The network will have a maximum speed of 8 GB, with scalable augmented reality and/or virtual reality (AR/VR) capabilities, with low to no latency in a bandwidth-constrained environment. The HP-SON architecture utilizes software-defined networking (SDN) and ML concepts to characterize current, and predict future network conditions, and then adapt traffic flow behaviors based on those characterizations to achieve performance goals. The result is the efficient usage of network resources and an improved overall user experience. While initially intended for application to the STE, HP-SON aims to be network agnostic.? Consequently, this approach is believed to have wide commercial application to any IP network as a network performance acceleration appliance.