• Corpus ID: 239015863

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

  title={Deep Learning-Based Power Control for Uplink Cell-Free Massive MIMO Systems},
  author={Yongshun Zhang and Jiayi Zhang and Yu Jin and Stefano Buzzi and Bo Ai},
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… 

Figures and Tables from this paper


Deep Learning-based Power Control for Cell-Free Massive MIMO Networks
A deep learning (DL) based power control algorithm that solves the max-min user fairness problem in a cell-free massive multiple-input multiple-output (MIMO) system is proposed, which achieves a performance-complexity trade-off with around 400 times faster implementation and comparable performance to the optimization-based algorithm.
Uplink Power Control in Cell-Free Massive MIMO via Deep Learning
Numerical results show that the presence of the pilot contamination in the cell-free massive MIMO system does not significantly affect the learning capabilities of the neural network, that gives near-optimal performance.
Deep Learning Power Allocation in Massive MIMO
This work advocates the use of deep learning to perform max-min and max-prod power allocation in the downlink of Massive MIMO networks, and significantly improves the complexity-performance trade-off of power allocation, compared to traditional optimization-oriented methods.
Power Allocation in Cell-Free Massive MIMO: A Deep Learning Method
A deep neural network (DNN) is proposed that approximates very closely the results of a commonly used heuristic based on the bisection algorithm for massive MIMO power allocation.
Pilot Power Control for Cell-Free Massive MIMO
This correspondence paper considers a cell-free massive Multiple-Input Multiple-Output (MIMO) system where access points (APs) serve a much smaller number of users under the time-division duplex operation, and proposes a pilot power control design, which chooses the pilotPower control coefficients to minimize the mean-squared error of the channel estimation.
Unsupervised-Learning Power Control for Cell-Free Wireless Systems
This paper studies the viability of feedforward neural networks for centralized power control in the uplink of cell-free wireless systems with matched-filter reception, and finds that the NN closely approximates the optimum solutions produced by convex solvers while vastly reducing the complexity.
Sum-Rate Maximization in Cell-Free Massive MIMO with Low-Resolution ADCs and ZF Receiver
Simulation results exhibit that the proposed SCA algorithm can substantially improve the uplink sum-rate of the considered system.
Unsupervised Learning for C-RAN Power Control and Power Allocation
This letter applies a feedforward neural network trained in an unsupervised fashion to the problem of optimizing the transmit powers in centralized radio access networks operating on a cell-free basis, finding the performance is very satisfactory and the scalability is manifestly superior to that of convex solvers.
Channel Estimation for Cell-Free mmWave Massive MIMO Through Deep Learning
Extensive simulation results validate that the training speed of FFD net is faster than state-of-the-art channel estimators without sacrificing normalized mean square error performance, which makes FFDNet as an practical channel estimator for cell-free mmWave massive MIMO systems.
Structured Massive Access for Scalable Cell-Free Massive MIMO Systems
The proposed initial access algorithm and pilot assignment schemes outperform their corresponding benchmarks, P-LSFD achieves scalability with a negligible performance loss compared to the conventional optimal large-scale fading decoding, and scalable fractional power control provides a controllable trade-off between user fairness and the average SE.