Optimally Supporting IoT with Cell-Free Massive MIMO

TL;DR

This paper investigates optimizing IoT support using cell-free massive MIMO systems, proposing novel power control algorithms and neural network techniques for efficient uplink and downlink performance.

Contribution

It introduces new max-min power control algorithms and scalable neural network-based solutions for efficient resource management in cell-free massive MIMO IoT systems.

Findings

Uplink SINR approximation using large-scale fading coefficients.

Neural network-based power control reduces computation time by 30 times.

Scalable NN algorithm for large networks, with acceptable sub-optimal performance.

Abstract

We study internet of things (IoT) systems supported by cell-free (CF) massive MIMO (mMIMO) with optimal linear channel estimation. For the uplink, we consider optimal linear MIMO receiver and obtain an uplink SINR approximation involving only large-scale fading coefficients using random matrix (RM) theory. Using this approximation we design several max-min power control algorithms that incorporate power and rate weighting coefficients to achieve a target rate with high energy efficiency. For the downlink, we consider maximum ratio (MR) beamforming. Instead of solving a complex quasi-concave problem for downlink power control, we employ a neural network (NN) technique to obtain comparable power control with around 30 times reduction in computation time. For large networks we proposed a different NN based power control algorithm. This algorithm is sub-optimal, but its big advantage is that it is scalable.