# Deep Learning-Based Power Control for Uplink Cell-Free Massive MIMO Systems

arXiv: https://arxiv.org/abs/2110.09001 · HTML: https://mlsanity.com/paper/2110.09001/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 8 of 8)

- [Scalable Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/1908.03119/) (2019)
- [Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementation](https://mlsanity.com/paper/1903.10611/) (2019)
- [Deep Learning Power Allocation in Massive MIMO](https://mlsanity.com/paper/1812.03640/) (2018)
- [Prospective Multiple Antenna Technologies for Beyond 5G](https://mlsanity.com/paper/1910.00092/) (2019)
- [Deep Learning-based Power Control for Cell-Free Massive MIMO Networks](https://mlsanity.com/paper/2102.10366/) (2021)
- [Uplink power control in cell-free massive MIMO via deep learning](https://mlsanity.com/paper/1908.11121/) (2019)
- [Structured Massive Access for Scalable Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/2006.10275/) (2020)
- [UAV Communications with WPT-aided Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/2104.11513/) (2021)

## Abstract (arXiv)

In this paper, a general framework for deep learning-based power control methods for max-min, max-product and max-sum-rate optimization in uplink cell-free massive multiple-input multiple-output (CF mMIMO) systems is proposed. Instead of using supervised learning, the proposed method relies on unsupervised learning, in which optimal power allocations are not required to be known, and thus has low training complexity. More specifically, a deep neural network (DNN) is trained to learn the map between fading coefficients and power coefficients within short time and with low computational complexity. It is interesting to note that the spectral efficiency of CF mMIMO systems with the proposed method outperforms previous optimization methods for max-min optimization and fits well for both max-sum-rate and max-product optimizations.