End-to-End Deep Learning for Multipair Two-Way Massive MIMO with PA Impairments

Multipair (MP) massive multiple-input-multiple-output (MIMO) two-way relaying system is a promising solution that is able to provide excellent spectral efficiency performance. It consists in multiple pairs (<inline-formula><tex-math notation="LaTeX">2K</tex-math></inli...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE systems journal Ročník 17; číslo 2; s. 1 - 10
Hlavní autori: Cherif, Maha, Arfaoui, Ahlem, Zayani, Rafik, Bouallegue, Ridha
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.06.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Antennas
Artificial neural networks
Communications systems
Deep learning
deep learning (DL)
Downlink
end to end (E2E)
Engineering Sciences
Fading
Machine learning
Massive MIMO
massive multiple-input–multiple-output (MIMO)
MIMO communication
Multipair
Peak to average power ratio
power amplifier
Power amplifiers
Precoding
Rayleigh channels
Relay
Relaying
Relays
Signal and Image processing
Uplink
ISSN:1932-8184, 1937-9234, 1937-9234, 1932-8184
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Multipair (MP) massive multiple-input-multiple-output (MIMO) two-way relaying system is a promising solution that is able to provide excellent spectral efficiency performance. It consists in multiple pairs (<inline-formula><tex-math notation="LaTeX">2K</tex-math></inline-formula>) of single-antenna user terminals that exchange information through of a relay using a large number of antennas <inline-formula><tex-math notation="LaTeX">M_{t}\gg 2K</tex-math></inline-formula>. The relay is equipped with a large number of energy-efficient power amplifiers (PAs) and ensure the multipair two-way forwarding. In this article, we first present an analytical study focused on the effects of PAs on the considered system over block fading Rayleigh channel. We derive closed-form expressions for the symbol error rate. Then, we develop a new efficient distributed learning approach for MP two-way massive MIMO. Specifically, we design the MP two-way massive MIMO system by leveraging the concept of the autoencoder, whereas the end-to-end communication system is designed using one deep neural network (NN). Interestingly, the proposed scheme, referred to as AE-MP-mMIMO, is suited for varying block fading Rayleigh channel scenarios. Indeed, we propose to adopt one stage precoder/decoder for each UE and two-stage precoding scheme for the relay: 1) an NN-Tx is used to address the PA nonlinearity and 2) a linear zero-forcing precoder is adopted to remove the multiuser interference. The NN-Tx and the UE's precoder/decoder are trained off-line and when the channel varies, only the zero-forcing precoder changes on-line. Numerical simulations show the capability of the proposed approach to achieve competitive performance with a significantly lower complexity compared to existing literature.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1932-8184
1937-9234
1937-9234
1932-8184
DOI:10.1109/JSYST.2022.3232590