Distributed Downlink Precoding for Cell-Free Massive MIMO: A Quasi-Neural Network Approach
- 14 August 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (2) , 1157-1168
Abstract
This paper proposes a novel downlink precoding method for a cell-free massive multiple-input multiple-output (CF-mMIMO) network, requiring no channel state information sharing between the access points via fronthaul links. By drawing analogies between a CF-mMIMO network and an artificial neural network, the proposed algorithm borrows the idea of backpropagation to train the precoders and the combiners through over-the-air ping-pong signaling between the access points and user equipments. It utilizes manifolds optimization to meet the per-AP power constraint and is named as distributed quasi-neural network precoding on manifold (DQNPM). The DQNPM algorithm can accommodate a large category of objective functions for fully distributed implementation. Numerical simulations show that our method outperforms the state-of-the-art approaches, and is robust against pilot contamination.Keywords
This publication has 33 references indexed in Scilit:
- Distributed Learning for MIMO Relay NetworksIEEE Journal of Selected Topics in Signal Processing, 2022
- A comprehensive survey on resource allocation for CRAN in 5G and beyond networksJournal of Network and Computer Applications, 2020
- A Brief Introduction to Manifold OptimizationJournal of the Operations Research Society of China, 2020
- User-Centric Cell-Free Massive MIMO with Interference Cancellation and Local ZF Downlink Precoding2018
- Introduction to Riemannian Manifolds2018
- Fundamentals of Massive MIMO2016
- Accelerated gradient methods for nonconvex nonlinear and stochastic programmingMathematical Programming, 2015
- Complex-Valued Matrix Derivatives2011
- Compressed Channel Sensing: A New Approach to Estimating Sparse Multipath ChannelsProceedings of the IEEE, 2010
- Handover in IP RAN2004