AI - Driven Self-Optimizing Receivers for Cognitive Radio Networks

Abstract

Cognitive radios (CRs) based on reconfigurable radio frequency (RF) electronics are a key requirement for implementing next-generation dynamic spectrum access (DSA) algorithms that improve management of the congested sub-6 GHz wireless spectrum. Suitable CRs incorporate adaptive components such as tunable notch filters, matching networks, and dynamic beamformers that can be intelligently tuned by RF scene analysis and situational awareness algorithms. Here we propose CR receivers that use machine learning (ML)-based modulation recognition (MR) algorithms for wideband real-time monitoring of spectral usage. The proposed systems enable detection and avoidance of anomalous signals. They also increase channel capacity and wireless data rates by exploiting white spaces in both licensed and unlicensed bands. An artificial intelligence (AI)-driven single-channel CR receiver prototype operating around 3 GHz has been implemented and tested. Experimental results show i) good over-the-air MR accuracy for several common modulation schemes using a deep belief network (DBN); and ii) autonomous self-optimization of the tunable RF front-end.