Smart Link Adaptation and Scheduling for IIoT

In this work, we present a machine learning enabled smart link adaption (LA) and scheduling approach for industrial Internet of things (IIoT), leveraging quasi-periodicity of traffic patterns in such environments. Our proposed algorithm consists of the following steps: i) reduced complexity link establishment (attachment) accounting jointly for beamforming and load management; ii) interference prediction using long short term memory neural networks; iii) semi-coordinated scheduling based on node grouping for interference avoidance. Our numerical results indicate that we can substantially improve the average spectral efficiency, e.g., by as much as 62% in a realistic IIoT scenario at the cost of very low additional overhead.