Machine-Learning-Based Cognitive Spectrum Assignment for 5G URLLC Applications

Abstract

As one of the main scenarios in 5G mobile networks, ultra-reliable low-latency communication (URLLC) can satisfy the stringent requirements of many emerging applications. To ensure end-to-end secure delivery of critical data, 5G URLLC needs an efficient hybrid access scheme for licensed and unlicensed spectrum in mmWave bands. This article introduces machine learning (ML) and fountain codes into mmWave hybrid access, and proposes an adaptive channel assignment method. The proactively predictive power of ML can reduce the transmission delay, and the rateless characteristic of fountain codes can ensure transmission reliability without retransmission. Finally, through a vehicle- to-everything use case, the proposed method is demonstrated to clearly ensure the URLLC transmission requirements for critical data.