In this Phase I effort, Tiami, LLC, aims to develop and demonstrate a hardware proof of concept for a completely distributed spectrum sensing scheme that leverages consensus learning amongst radio frequency (RF) sensors. The algorithm is based on low-bandwidth message exchange between one-hop neighbors, spans multiple RF bands, is agnostic to the sensing modality, and is resilient to link disruptions. Wireless multi-hop networks are widely used by the Navy for tactical data links and exchange of track measurements or engage-on-remote data. Spectrum domain awareness is crucial for link reliability and anti-jamming measures, however, the distributed nature of multi-hop networks and the need for robustness rules out a centralized spectrum sensing approach. Distributed spectrum sensing is a natural solution, but maintaining coherency across non-colocated nodes with intermittent links is a major technical challenge. Our proposed multi-agent consensus learning scheme for distributed spectrum sensing works as follows. M sensors or agents attempt to collaboratively learn the spectrum occupancy state of N frequency bands. Each sensor exchanges its local sensing likelihood per band with its one-hop neighbors in an iterative process, and updates its local statistic based on a weighted combination of its neighbor observations. Weights are adjusted based on network topology and outlier detection. Convergence is achieved when connected nodes arrive at a consensus.
Benefit: Anticipated
Benefits: Consensus scheme is agnostic to spectrum sensing method used by individual sensors. Accommodate an arbitrary sensing modality - machine learning, energy detection, etc. Sensors exchange a single fractional decimal per RF band per iteration. Deterministic and marginal communication overhead. Tolerant to link failures, heterogenous spectrum occupancy, and RF impairments. Robustness in tactical, high mobility, and jammed environments. Tiamis first priority is to work with defense primes in Phase II/III to transition the consensus sensing prototype to an advanced module that can be integrated with Navy PoR RF hardware. A second priority is transitioning the technology to other DoD components such as the Army, with prospective customers in C5ISR, Communications-Electronics Command, PEO C3T, PEO IEW&S, and Air Force (PEO C3I & Networks, PEO ISR & SOF). Commercial industry customers include 5G and 6G telecom companies who deploy sensors to detect military radar systems. The commercial RF sensing market is competitive. Examples are RF signal classification products from DeepSig and Epiq Solutions currently in the commercial market. DeepSig OmniSIG Sensor applies machine learning techniques for RF signature detection; however, it is a standalone sensor without consensus learning. The global 5G radio access network market size was valued at $12.5 billion in 2022 and is expected to expand at a compound annual growth rate (CAGR) of 18.4% from 2023 to 2030 (Grandviewresearch). Additional market opportunities beyond the DoD include commercial applications where a 5G sensor network needs to detect the presence of radar emitters, as in the CBRS and AMBIT/EMBRSS S-band spectrum.
Keywords: consensus, consensus, distributed sensors, Cognitive Radio, learning, Spectrum sensing
