End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance

Ankit Gupta; Mathini Sellathurai

doi:10.1109/SPAWC51858.2021.9593107

End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance

Ankit Gupta
, Mathini Sellathurai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In this work, we design an end-to-end (E2E) learning-based two-way amplify-and-forward (TWAF) relay network in the presence of I/Q imbalance (IQI) by maximizing the generalized mutual information between the input-output bits. The proposed system employs neural network (NN)-based terminal nodes impacted by the IQI and a TWAF relay node that only retransmits the amplified received signals (no additional processing at the relay nodes). Also, we propose four specific lambda layers at the NN decoders to pre-process the received signals. In particular, we propose to design coded-modulation and decoded-demodulation for the NN encoders and NN decoders of both the terminal nodes jointly, to tackle the interference of simultaneously received signals at the TWAF relay node and remove the deteriorating impacts of IQI at the terminal nodes. The simulation results show that the proposed E2E learning framework outperforms the maximum likelihood detector with no IQI by at least 3 dB.

Original language	English
Title of host publication	22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2021)
Publisher	IEEE
Pages	111-115
Number of pages	5
ISBN (Electronic)	9781665428514
DOIs	https://doi.org/10.1109/SPAWC51858.2021.9593107
Publication status	Published - 15 Nov 2021
Event	22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications 2021 - Lucca, Italy Duration: 27 Sept 2021 → 30 Sept 2021

Conference

Conference	22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications 2021
Abbreviated title	SPAWC 2021
Country/Territory	Italy
City	Lucca
Period	27/09/21 → 30/09/21

Keywords

amplify-and-forward
and I/Q imbalance
Autoencoder
end-to-end learning
relay networks
two-way

ASJC Scopus subject areas

Electrical and Electronic Engineering
Computer Science Applications
Information Systems

Access to Document

10.1109/SPAWC51858.2021.9593107

Cite this

@inproceedings{733eaff20dd44a218574e50b5bf16c78,

title = "End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance",

abstract = "In this work, we design an end-to-end (E2E) learning-based two-way amplify-and-forward (TWAF) relay network in the presence of I/Q imbalance (IQI) by maximizing the generalized mutual information between the input-output bits. The proposed system employs neural network (NN)-based terminal nodes impacted by the IQI and a TWAF relay node that only retransmits the amplified received signals (no additional processing at the relay nodes). Also, we propose four specific lambda layers at the NN decoders to pre-process the received signals. In particular, we propose to design coded-modulation and decoded-demodulation for the NN encoders and NN decoders of both the terminal nodes jointly, to tackle the interference of simultaneously received signals at the TWAF relay node and remove the deteriorating impacts of IQI at the terminal nodes. The simulation results show that the proposed E2E learning framework outperforms the maximum likelihood detector with no IQI by at least 3 dB.",

keywords = "amplify-and-forward, and I/Q imbalance, Autoencoder, end-to-end learning, relay networks, two-way",

author = "Ankit Gupta and Mathini Sellathurai",

note = "Funding Information: ACKNOWLEDGEMENT This work was supported in part by the U.K. Engineering and Physical Sciences Research Council under Grant EP/P009670/1 and in part by the U.K.-India Education and Research Initiative Thematic Partnerships under Grant UGC -UKIERI 2016-17-058. REFERENCES [1] T. O{\textquoteright}Shea and J. Hoydis, “An Introduction to Deep Learning for the Physical Layer,” in IEEE Transactions on Cognitive Communications and Networking, vol. 3, no. 4, pp. 563–575, Dec. 2017. [2] S. Cammerer, F. A. Aoudia, S. D{\"o}rner, M. Stark, J. Hoydis and S. ten Brink, “Trainable Communication Systems: Concepts and Prototype,” in IEEE Trans. Commun., vol. 68, no. 9, pp. 5489–5503, Sept. 2020. [3] A. Gupta and M. Sellathurai, “End-to-End Learning-Based Framework for Amplify-and-Forward Relay Networks,” in IEEE Access, vol. 9, pp. 81660–81677, 2021 [4] A. Gupta and M. Sellathurai, “End-to-End Learning-based Amplify-and-Forward Relay Networks using Autoencoders,” ICC 2020 - 2020 IEEE Intern. Conf. Commun. (ICC), Dublin, Ireland, 2020, pp. 1–6. [5] T. Matsumine, T. Koike-Akino and Y. Wang, “Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks,” ICC 2019 - 2019 IEEE International Conference on Communications (ICC), Shanghai, China, 2019, pp. 1–6. [6] A. E. Canbilen, et. al., “Impact of I/Q Imbalance on Amplify-and-Forward Relaying: Optimal Detector Design and Error Performance,” in IEEE Trans. Commun., vol. 67, no. 5, pp. 3154-3166, May 2019. [7] J. Li, M. Matthaiou and T. Svensson, “I/Q Imbalance in AF Dual-Hop Relaying: Performance Analysis in Nakagami-m Fading,” in IEEE Trans. Commun., vol. 62, no. 3, pp. 836-847, March 2014. [8] J. Qi, S. A{\"i}ssa and M. Alouini, “Impact of I/Q imbalance on the performance of two-way CSI-assisted AF relaying,” 2013 IEEE Wireless Commun. \& Network. Conf. (WCNC), Shanghai, 2013, pp. 2507-2512. [9] J. Li et. al., “I/Q Imbalance in Two-Way AF Relaying,” in IEEE Trans. Commun., vol. 62, no. 7, pp. 2271-2285, July 2014. [10] I. Goodfellow et. al., Deep Learning, The MIT Press, 2016. [11] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv, Dec. 2014, arXiv:1412.6980. Publisher Copyright: {\textcopyright} 2021 IEEE.; 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications 2021, SPAWC 2021 ; Conference date: 27-09-2021 Through 30-09-2021",

year = "2021",

month = nov,

day = "15",

doi = "10.1109/SPAWC51858.2021.9593107",

language = "English",

pages = "111--115",

booktitle = "22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2021)",

publisher = "IEEE",

address = "United States",

}

Gupta, A & Sellathurai, M 2021, End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance. in 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2021). IEEE, pp. 111-115, 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications 2021, Lucca, Italy, 27/09/21. https://doi.org/10.1109/SPAWC51858.2021.9593107

TY - GEN

T1 - End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance

AU - Gupta, Ankit

AU - Sellathurai, Mathini

N1 - Funding Information: ACKNOWLEDGEMENT This work was supported in part by the U.K. Engineering and Physical Sciences Research Council under Grant EP/P009670/1 and in part by the U.K.-India Education and Research Initiative Thematic Partnerships under Grant UGC -UKIERI 2016-17-058. REFERENCES [1] T. O’Shea and J. Hoydis, “An Introduction to Deep Learning for the Physical Layer,” in IEEE Transactions on Cognitive Communications and Networking, vol. 3, no. 4, pp. 563–575, Dec. 2017. [2] S. Cammerer, F. A. Aoudia, S. Dörner, M. Stark, J. Hoydis and S. ten Brink, “Trainable Communication Systems: Concepts and Prototype,” in IEEE Trans. Commun., vol. 68, no. 9, pp. 5489–5503, Sept. 2020. [3] A. Gupta and M. Sellathurai, “End-to-End Learning-Based Framework for Amplify-and-Forward Relay Networks,” in IEEE Access, vol. 9, pp. 81660–81677, 2021 [4] A. Gupta and M. Sellathurai, “End-to-End Learning-based Amplify-and-Forward Relay Networks using Autoencoders,” ICC 2020 - 2020 IEEE Intern. Conf. Commun. (ICC), Dublin, Ireland, 2020, pp. 1–6. [5] T. Matsumine, T. Koike-Akino and Y. Wang, “Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks,” ICC 2019 - 2019 IEEE International Conference on Communications (ICC), Shanghai, China, 2019, pp. 1–6. [6] A. E. Canbilen, et. al., “Impact of I/Q Imbalance on Amplify-and-Forward Relaying: Optimal Detector Design and Error Performance,” in IEEE Trans. Commun., vol. 67, no. 5, pp. 3154-3166, May 2019. [7] J. Li, M. Matthaiou and T. Svensson, “I/Q Imbalance in AF Dual-Hop Relaying: Performance Analysis in Nakagami-m Fading,” in IEEE Trans. Commun., vol. 62, no. 3, pp. 836-847, March 2014. [8] J. Qi, S. Aïssa and M. Alouini, “Impact of I/Q imbalance on the performance of two-way CSI-assisted AF relaying,” 2013 IEEE Wireless Commun. & Network. Conf. (WCNC), Shanghai, 2013, pp. 2507-2512. [9] J. Li et. al., “I/Q Imbalance in Two-Way AF Relaying,” in IEEE Trans. Commun., vol. 62, no. 7, pp. 2271-2285, July 2014. [10] I. Goodfellow et. al., Deep Learning, The MIT Press, 2016. [11] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv, Dec. 2014, arXiv:1412.6980. Publisher Copyright: © 2021 IEEE.

PY - 2021/11/15

Y1 - 2021/11/15

N2 - In this work, we design an end-to-end (E2E) learning-based two-way amplify-and-forward (TWAF) relay network in the presence of I/Q imbalance (IQI) by maximizing the generalized mutual information between the input-output bits. The proposed system employs neural network (NN)-based terminal nodes impacted by the IQI and a TWAF relay node that only retransmits the amplified received signals (no additional processing at the relay nodes). Also, we propose four specific lambda layers at the NN decoders to pre-process the received signals. In particular, we propose to design coded-modulation and decoded-demodulation for the NN encoders and NN decoders of both the terminal nodes jointly, to tackle the interference of simultaneously received signals at the TWAF relay node and remove the deteriorating impacts of IQI at the terminal nodes. The simulation results show that the proposed E2E learning framework outperforms the maximum likelihood detector with no IQI by at least 3 dB.

AB - In this work, we design an end-to-end (E2E) learning-based two-way amplify-and-forward (TWAF) relay network in the presence of I/Q imbalance (IQI) by maximizing the generalized mutual information between the input-output bits. The proposed system employs neural network (NN)-based terminal nodes impacted by the IQI and a TWAF relay node that only retransmits the amplified received signals (no additional processing at the relay nodes). Also, we propose four specific lambda layers at the NN decoders to pre-process the received signals. In particular, we propose to design coded-modulation and decoded-demodulation for the NN encoders and NN decoders of both the terminal nodes jointly, to tackle the interference of simultaneously received signals at the TWAF relay node and remove the deteriorating impacts of IQI at the terminal nodes. The simulation results show that the proposed E2E learning framework outperforms the maximum likelihood detector with no IQI by at least 3 dB.

KW - amplify-and-forward

KW - and I/Q imbalance

KW - Autoencoder

KW - end-to-end learning

KW - relay networks

KW - two-way

UR - https://www.scopus.com/pages/publications/85122798291

U2 - 10.1109/SPAWC51858.2021.9593107

DO - 10.1109/SPAWC51858.2021.9593107

M3 - Conference contribution

AN - SCOPUS:85122798291

SP - 111

EP - 115

BT - 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2021)

PB - IEEE

T2 - 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications 2021

Y2 - 27 September 2021 through 30 September 2021

ER -

End-to-End Learning-based Two-Way AF Relay Networks with I/Q Imbalance

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this