ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Enhanced deep soft interference cancellation for multiuser symbol detection

  • Jihyung Kim (Satellite Communication Research Division, Electronics and Telecommunications Research Institute) ;
  • Junghyun Kim (Department of Artificial Intelligence, Sejong University) ;
  • Moon-Sik Lee (Satellite Communication Research Division, Electronics and Telecommunications Research Institute)
  • Received : 2022.12.16
  • Accepted : 2023.05.15
  • Published : 2023.12.10
Download PDF
⟨ Previous Next ⟩

Abstract

The detection of all the symbols transmitted simultaneously in multiuser systems using limited wireless resources is challenging. Traditional model-based methods show high performance with perfect channel state information (CSI); however, severe performance degradation will occur if perfect CSI cannot be acquired. In contrast, data-driven methods perform slightly worse than model-based methods in terms of symbol error ratio performance in perfect CSI states; however, they are also able to overcome extreme performance degradation in imperfect CSI states. This study proposes a novel deep learning-based method by improving a state-of-the-art data-driven technique called deep soft interference cancellation (DSIC). The enhanced DSIC (EDSIC) method detects multiuser symbols in a fully sequential manner and uses an efficient neural network structure to ensure high performance. Additionally, error-propagation mitigation techniques are used to ensure robustness against channel uncertainty. The EDSIC guarantees a performance that is very close to the optimal performance of the existing model-based methods in perfect CSI environments and the best performance in imperfect CSI environments.

Keywords

Acknowledgement

This study was supported by an Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (No. 2021-0-00794, Development of 3D Spatial Mobile Communication Technology).

References

  1. X. Chen, R. Jia, and D. W. K. Ng, On the design of massive non-orthogonal multiple access with imperfect successive interference cancellation, IEEE Trans. Commun. 67 (2019), no. 3, 2539-2551. https://doi.org/10.1109/TCOMM.2018.2884476
  2. W.-J. Choi, K.-W. Cheong, and J. M. Cioffi, Iterative soft interference cancellation for multiple antenna systems, (Proceedings of the Wireless Communications and Networking Conference, Chicago IL, USA), 2000, pp. 304-309.
  3. I. Goodfellow, Y. Bengio, and A. Courville, Deep learning, MIT Press, Cambridge, 2016.
  4. D. Silver, J. Schrittwieser, K. Simonyan, I. Antonoglou, A. Huang, A. Guez, T. Hubert, L. Baker, M. Lai, A. Bolton, Y. Chen, T. Lillicrap, F. Hui, L. Sifre, G. V. D. Driessche, T. Graepel, and D. Hassabis, Mastering the game of Go without human knowledge, Nature 550 (2017), no. 7676, 354-359. https://doi.org/10.1038/nature24270
  5. O. Vinyals, I. Babuschkin, W. M. Czarnecki, M. Mathieu, A. Dudzik, J. Chung, D. H. Choi, R. Powell, T. Ewalds, P. Georgiev, J. Oh, D. Horgan, M. Kroiss, I. Danihelka, A. Huang, L. Sifre, T. Cai, J. P. Agapiou, M. Jaderberg, A. S. Vezhnevets, R. Leblond, T. Pohlen, V. Dalibard, D. Budden, Y. Sulsky, J. Molloy, T. L. Paine, C. Gulcehre, Z. Wang, T. Pfaff, Y. Wu, R. Ring, D. Yogatama, D. Wunsch, K. McKinney, O. Smith, T. Schaul, T. Lillicrap, K. Kavukcuoglu, D. Hassabis, C. Apps, and D. Silver, Grandmaster level in Starcraft II using multi-agent reinforcement learning, Nature 575 (2019), no. 7782, 350-354.
  6. Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature 521 (2015), no. 7553, 436-444. https://doi.org/10.1038/nature14539
  7. D. Gunduz, P. de Kerret, N. D. Sidiropoulos, D. Gesbert, C. R. Murthy, and M. van der Schaar, Machine learning in the air, IEEE J. Sel. Areas Commun. 37 (2019), no. 10, 2184-2199. https://doi.org/10.1109/JSAC.2019.2933969
  8. H. Lee, B. Lee, H. Yang, J. Kim, S. Kim, W. Shin, B. Shim, and H. V. Poor, Towards 6G hyper-connectivity: vision, challenges, and key enabling technologies, J. Commun. Netw., early access, (2023). DOI 10.23919/JCN.2023.000006.
  9. Q. Mao, F. Hu, and Q. Hao, Deep learning for intelligent wireless networks: a comprehensive survey, IEEE Commun. Surv. Tutor. 20 (2018), no. 4, 2595-2621. https://doi.org/10.1109/COMST.2018.2846401
  10. T. O'Shea and J. Hoydis, An introduction to deep learning for the physical layer, IEEE Trans. Cognit. Commun. Netw. 3 (2017), no. 4, 563-575. https://doi.org/10.1109/TCCN.2017.2758370
  11. M. Honkala, D. Korpi, and J. M. J. Huttunen, DeepRx: fully convolutional deep learning receiver, IEEE Trans. Wirel. Commun. 20 (2021), no. 6, 3925-3940. https://doi.org/10.1109/TWC.2021.3054520
  12. S. Han, J. Kim, and H.-Y. Song, A new design of channel denoiser using residual autoencoder, IET Electron. Lett. 59 (2023), no. 2, 1-3.
  13. E. Nachmani, E. Marciano, L. Lugosch, W. J. Gross, D. Burshtein, and Y. Be'ery, Deep learning methods for improved decoding of linear codes, IEEE J. Sel. Top. Signal Process. 12 (2018), no. 1, 119-131. https://doi.org/10.1109/JSTSP.2017.2788405
  14. S. Zhang, S. Chen, and X. Yang, Learn codes: inventing low-latency codes via recurrent neural networks, IEEE J. Sel. Areas Inform. Theory 1 (2020), no. 1, 207-216. https://doi.org/10.1109/JSAIT.2020.2988577
  15. S. Dorner, S. Cammerer, J. Hoydis, and S. Ten Brink, Deep learning based communication over the air, IEEE J. Sel. Top. Signal Process. 12 (2018), no. 1, 132-143. https://doi.org/10.1109/JSTSP.2017.2784180
  16. H. Kim, S. Oh, and P. Viswanath, Physical layer communication via deep learning, IEEE J. Sel. Areas Inform. Theory 1 (2020), no. 1, 5-18. https://doi.org/10.1109/JSAIT.2020.2991562
  17. J. Kim, B. Lee, H. Lee, Y. Kim, and J. Lee, Deep learning-assisted multi-dimensional modulation and resource mapping for advanced OFDM systems, (Proceedings of the IEEE GLobecom Workshops, Abu Dhabi, UAE), 2018, pp. 1-6.
  18. H. Ye, L. Liang, G. Y. Li, and B.-H. Juang, Deep learning-based end-to-end wireless communication systems with conditional gans as unknown channels, IEEE Trans. Wirel. Commun. 19 (2020), no. 5, 3133-3143. https://doi.org/10.1109/TWC.2020.2970707
  19. W. Lee, M. Kim, and D.-H. Cho, Deep power control: transmit power control scheme based on convolutional neural network, IEEE Commun. Lett. 22 (2018), no. 6, 1276-1279. https://doi.org/10.1109/LCOMM.2018.2825444
  20. F. Liang, C. Shen, W. Yu, and F. Wu, Towards optimal power control via ensembling deep neural networks, IEEE Trans. Commun. 68 (2020), no. 3, 1760-1776. https://doi.org/10.1109/TCOMM.2019.2957482
  21. Y. Shen, Y. Shi, J. Zhang, and K. B. Letaief, Graph neural networks for scalable radio resource management: architecture design and theoretical analysis, IEEE J. Sel. Areas Commun. 39 (2021), no. 1, 101-115. https://doi.org/10.1109/JSAC.2020.3036965
  22. H. Sun, X. Chen, Q. Shi, M. Hong, X. Fu, and N. D. Sidiropoulos, Learning to optimize: training deep neural networks for interference management, IEEE Trans. Signal Process. 66 (2018), no. 20, 5438-5453. https://doi.org/10.1109/TSP.2018.2866382
  23. C. Lin, Q. Cheng, and X. Li, A deep learning approach for MIMO-NOMA downlink signal detection, Sensors 19 (2021), no. 11, 1-22.
  24. T. V. Luong, N. Shlezinger, C. Xu, T. M. Hoang, Y. C. Eldar, and L. Hanjo, Deep learning based successive interference cancellation for the non-orthogonal downlink, IEEE Trans. Vehic. Technol. 71 (2022), no. 11, 11876-11888. https://doi.org/10.1109/TVT.2022.3193201
  25. N. Shlezinger, R. Fu, and Y. C. Eldar, DeepSIC: deep soft interference cancellation for multiuser MIMO detection, IEEE Trans. Wirel. Commun. 20 (2021), no. 2, 1349-1362. https://doi.org/10.1109/TWC.2020.3032663
  26. W. Lee, K. Lee, and T. Q. S. Quek, Deep-learning-assisted wireless-powered secure communications with imperfect channel state information, IEEE Int. Things J. 9 (2022), no. 13, 11464-11476. https://doi.org/10.1109/JIOT.2021.3128936
  27. N. Shlezinger, R. Fu, and Y. C. Eldar, Hybrid beamforming based on an unsupervised deep learning network for downlink channels with imperfect CSI, IEEE Wirel. Commun. Lett. 11 (2022), no. 7, 1543-1547. https://doi.org/10.1109/LWC.2022.3179362
  28. 3GPP, Technical Specification Group Radio Access Network; NR; multiplexing and channel coding; (Release 17), Technical Specification (TS) 38.212, 3rd Generation Partnership Project (3GPP), version 17.4.0, December 2022.