# Sum Spectral Efficiency Maximization in Massive MIMO Systems: Benefits from Deep Learning

## TL;DR

This paper develops a deep learning-based method for joint data and pilot power optimization in Massive MIMO systems, achieving near-optimal spectral efficiency with real-time computational speed.

## Contribution

It introduces a novel deep learning approach trained on an optimization algorithm to enable fast, online power control in multi-cell Massive MIMO systems.

## Key findings

- Neural network achieves 1% loss compared to stationary point in four-cell systems.
- Neural network incurs 2% sum SE loss in nine-cell systems.
- Proposed method enables sub-millisecond runtime for power optimization.

## Abstract

This paper investigates the joint data and pilot power optimization for maximum sum spectral efficiency (SE) in multi-cell Massive MIMO systems, which is a non-convex problem. We first propose a new optimization algorithm, inspired by the weighted minimum mean square error (MMSE) approach, to obtain a stationary point in polynomial time. We then use this algorithm together with deep learning to train a convolutional neural network to perform the joint data and pilot power control in sub-millisecond runtime, making it suitable for online optimization in real multi-cell Massive MIMO systems. The numerical result demonstrates that the solution obtained by the neural network is $1\%$ less than the stationary point for four-cell systems, while the sum SE loss is $2\%$ in a nine-cell system.