• Corpus ID: 248496247

Heterogeneous graph neural network for power allocation in multicarrier-division duplex cell-free massive MIMO systems

  title={Heterogeneous graph neural network for power allocation in multicarrier-division duplex cell-free massive MIMO systems},
  author={Bohan Li and Lie-liang Yang and Robert G. Maunder and Songlin Sun and Pei Xiao},
—In-band full duplex-based cell-free (IBFD- CF) systems suffer from severe interference problem including self-interference (SI) and cross-link interfer- ence (CLI), especially when cell-free (CF) systems are operated in a distributed way. To this end, we pro- pose multicarrier-division duplex (MDD) as an enabler for full-duplex (FD)-style operation in distributed CF massive MIMO systems, where DL and UL transmissions take place simultaneously at the same fre- quency band but mutually orthogonal… 



Dynamic Power Allocation for Cell-Free Massive MIMO: Deep Reinforcement Learning Methods

This paper explores the use of data-driven methods since they can achieve near-optimal performance with a low computational complexity in power allocation and finds that the well-trained DRL methods achieved at least a 33% higher sum-SE than the WMMSE algorithm.

On the Spectral and Energy Efficiencies of Full-Duplex Cell-Free Massive MIMO

A novel and comprehensive optimization problem for the maximization of SE and EE in which power control, access point-UE (AP-UE) association and AP selection are jointly optimized under a realistic power consumption model, resulting in a difficult class of mixed-integer nonconvex programming.

Performance of Network-Assisted Full-Duplex for Cell-Free Massive MIMO

The spectral efficiency of network assisted full-duplex communications (NAFD) in cell-free (CF) massive multiple-input multiple-output (MIMO) network with imperfect channel state information is investigated under spatial correlated channels and a novel genetic algorithm based user scheduling strategy (GAS) is proposed.

Unfolding WMMSE Using Graph Neural Networks for Efficient Power Allocation

This work puts forth a neural network architecture inspired by the algorithmic unfolding of the iterative weighted minimum mean squared error (WMMSE) method, that is permutation equivariant, thus facilitating generalizability across network topologies.

Downlink Power Control for Cell-Free Massive MIMO With Deep Reinforcement Learning

This paper proposes a model-free method adopting the deep deterministic policy gradient algorithm (DDPG) with feedforward neural networks (NNs) to solve the downlink max-min power control problem in CF massive MIMO systems and extends the DDPG algorithm to both themax-sum and the max-product power control problems, while achieving better performance than that achieved by the conventional deep learning algorithm.

Full Duplex and Dynamic TDD: Pushing the Limits of Spectrum Reuse in Multi-Cell Communications

It is shown that the cross-link interference for both duplexing modes, especially from base station to base station, is the remaining challenge in multi-cell networks, restricting the uplink performance, and that beamforming techniques of low complexity can be used to enable a smooth introduction of full duplex into cellular systems.

Cell-Free Massive MIMO: A Survey

A comprehensive survey of different aspects of the CF mMIMO system from the general system model, the detailed system operation, the limitations towards a practically implemented system to the potential of integrating the system with emerging techniques/technologies.

Foundations of User-Centric Cell-Free Massive MIMO

This monograph covers the foundations of User-centric Cell-free Massive MIMO, starting from the motivation and mathematical definition, and describes the state-of-the-art signal processing algorithms for channel estimation, uplink data reception.

Self-Interference Cancellation and Channel Estimation in Multicarrier-Division Duplex Systems With Hybrid Beamforming

An adaptive beamforming assisted SI cancellation scheme with taking into account the practical requirement of analog-to-digital conversion (ADC) is proposed and it can be shown that the proposed approach is capable of jointly coping with the desired signals’ transmission and SI suppression.

Power-Efficient Distributed Beamforming for Full-Duplex MIMO Relaying Networks

This paper comes up with two iterative distributed beamforming algorithms, Algorithm 1 for relays equipped with single receive antenna and Algorithm 2 with multiple receive antennas that are scalable for different network sizes and topologies and can yield a global optimal solution of the power minimization problem.