Learning to Beamform in Joint Multicast and Unicast Transmission With Imperfect CSI

With the rapid development of mobile Internet, the demand for multicast is growing rapidly, such as content pushing and video streaming. The multicast service is usually offered to users without interrupting their on-going unicast transmission, and thus the multicast and unicast beamformers needs to...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on communications Vol. 71; no. 5; pp. 2711 - 2723
Main Authors: Zhang, Zhe, Tao, Meixia, Liu, Ya-Feng
Format: Journal Article
Language:English
Published: New York IEEE 01.05.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Array signal processing
Beamforming
Channel estimation
Graph neural networks
imperfect CSI
Interference
Joint multicast and unicast transmission
Learning
Multicast algorithms
Multicasting
Neural networks
Optimization
Permutations
UMGNN
Unicast
Video transmission
ISSN:0090-6778, 1558-0857
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid development of mobile Internet, the demand for multicast is growing rapidly, such as content pushing and video streaming. The multicast service is usually offered to users without interrupting their on-going unicast transmission, and thus the multicast and unicast beamformers needs to be jointly designed, which generally requires perfect channel state information (CSI). However, perfect CSI is usually unavailable due to the channel estimation error. In this paper, we propose a learning based approach to jointly design the multicast and unicast beamformers with imperfect CSI. To learn the beamforming strategy, a new graph neural network (GNN) based architecture named unicast-multicast GNN (UMGNN) is proposed, which only requires the estimated channel. UMGNN can guarantee the permutation invariance/equivalence and model the special property in the multicast transmission, i.e., the multicast rate is determined by the worst user. Moreover, by sharing the parameters across different users, UMGNN exhibits a pretty good scalability to different number of users. Numerical results show that UMGNN outperforms a fully connected neural network and a widely used sampling-based algorithm. To highlight its performance in the multicast transmission, we also show that UMGNN can find the correct worst user that determines the multicast rate.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0090-6778
1558-0857
DOI:10.1109/TCOMM.2023.3251995