ETRI Journal

  • 제44권6호
  • /
  • Pages.915-924
  • /
  • 2022
  • /
  • 1225-6463(pISSN)
  • /
  • 2233-7326(eISSN)
한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

Deep learning-based scalable and robust channel estimator for wireless cellular networks

  • Anseok, Lee (Intelligent Wireless Access Research Section, Mobile Communication Research Division, Telecommunications & Media Research Laboratory, Electronics and Telecommunications Research Institute) ;
  • Yongjin, Kwon (Intelligent Wireless Access Research Section, Mobile Communication Research Division, Telecommunications & Media Research Laboratory, Electronics and Telecommunications Research Institute) ;
  • Hanjun, Park (Intelligent Wireless Access Research Section, Mobile Communication Research Division, Telecommunications & Media Research Laboratory, Electronics and Telecommunications Research Institute) ;
  • Heesoo, Lee (Intelligent Wireless Access Research Section, Mobile Communication Research Division, Telecommunications & Media Research Laboratory, Electronics and Telecommunications Research Institute)
  • 투고 : 2022.05.24
  • 심사 : 2022.10.21
  • 발행 : 2022.12.10
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, we present a two-stage scalable channel estimator (TSCE), a deep learning (DL)-based scalable, and robust channel estimator for wireless cellular networks, which is made up of two DL networks to efficiently support different resource allocation sizes and reference signal configurations. Both networks use the transformer, one of cutting-edge neural network architecture, as a backbone for accurate estimation. For computation-efficient global feature extractions, we propose using window and window averaging-based self-attentions. Our results show that TSCE learns wireless propagation channels correctly and outperforms both traditional estimators and baseline DL-based estimators. Additionally, scalability and robustness evaluations are performed, revealing that TSCE is more robust in various environments than the baseline DL-based estimators.

키워드

과제정보

This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (2021-0-00972, Development of Intelligent Wireless Access Technologies)

참고문헌

  1. ETRI, [5G insight white paper 2.0] 5G technologies and its wayforward, 2017.
  2. ETRI, 6G insight: Vision and technologies, 2020.
  3. R. Shafin, L. Liu, V. Chandrasekhar, H. Chen, J. Reed, and J. C. Zhang, Artificial intelligence-enabled cellular networks: A critical path to beyond-5G and 6G, IEEE Wirel. Commun. 27 (2020), no. 2, 212-217. https://doi.org/10.1109/mwc.001.1900323
  4. Qualcomm, New SI: Study on artificial intelligence (AI)/Machine Learning (ML) for NR air interface, RP-213599. 3GPP, 2021.
  5. H. Ye, G. Y. Li, and B. H. Juang, Power of deep learning for channel estimation and signal detection in OFDM systems, IEEE Wirel. Commun. Lett. 7 (2018), no. 1, 114-117. https://doi.org/10.1109/lwc.2017.2757490
  6. M. Soltani, V. Pourahmadi, A. Mirzaei, and H. Sheikhzadeh, Deep learning-based channel estimation, IEEE Commun. Lett. 23 (2019), no. 4, 652-655. https://doi.org/10.1109/lcomm.2019.2898944
  7. C. Dong, C. C. Loy, K. He, and X. Tang, Image super-resolution using deep convolutional networks, IEEE Trans Pattern Anal Machine Intell 38 (2016), no. 2, 295-307. https://doi.org/10.1109/TPAMI.2015.2439281
  8. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising, IEEE Trans. Image Process. 26 (2017), no. 7, 3142-3155. https://doi.org/10.1109/TIP.2017.2662206
  9. L. Li, H. Chen, H.-H. Chang, and L. Liu, Deep residual learning meets OFDM channel estimation, IEEE Wirel. Commun. Lett. 9 (2020), no. 5, 615-618. https://doi.org/10.1109/lwc.2019.2962796
  10. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition), 2016, pp. 770-778.
  11. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. WardeFarley, S. Ozair, A. Courville, and Y. Bengio, Generative Adversarial Networks, arXive preprint, 2014. https://doi.org/10.48550/arXiv.1406.2661
  12. E. Balevi and J. G. Andrews, Wideband channel estimation with a generative adversarial network, IEEE Trans Wirel Commun 20 (2021), no. 5, 3049-3060. https://doi.org/10.1109/TWC.2020.3047100
  13. A. Radford, L. Metz, and S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, (International Conference on Learning Representations), 2016. https://doi.org/10.48550/arXiv.1511.06434
  14. S. Zhao, Y. Fang, and L. Qiu, Deep learning-based channel estimation with SRGAN in OFDM systems, (IEEE Wireless Communications and Networking Conference, Nanjing, China), 2021. https://doi.org/10.1109/WCNC49053.2021.9417242
  15. C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, and W. Shi, Photo-realistic single image super-resolution using a generative adversarial network, (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA), 2017, pp. 4681-4690.
  16. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, Adv. Neural Inform. Process. Syst. 30 (2017). https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
  17. J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, BERT: Pretraining of deep bidirectional transformers for language understanding, (Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies), 2019, pp. 4171-4186.
  18. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, An image is worth 1616 words: Transformers for image recognition at scale, arXive preprint ICLR, 2021. https://doi.org/10.48550/arXiv.2010.11929
  19. A. Yang, P. Sun, T. Rakesh, B. Sun, and F. Qin, Deep learning based OFDM channel estimation using frequency-time division and attention mechanism, (IEEE GLOBECOM Workshops, Madrid, Spain), 2021. https://doi.org/10.1109/GCWkshps52748.2021.9682149
  20. J. Li and Q. Peng, Lightweight channel estimation networks for OFDM systems, IEEE Wirel. Commun. Lett. 11 (2022), no. 10, 2066-2070. https://doi.org/10.1109/LWC.2022.3193199
  21. Z. Chen, F. Gu, and R. Jiang, Channel estimation method based on transformer in high dynamic environment, (12th International Conference on Wireless Communications and Signal Processing, Nanjing, China), 2020, pp. 817-822.
  22. D. Luan and J. Thompson, Attention based neural networks for wireless channel estimation, arXive preprint, 2022. https://doi.org/10.48550/arXiv.2204.13465
  23. K. C. Hung and D. W. Lin, Pilot-based LMMSE channel estimation for OFDM systems with powerdelay profile approximation, IEEE Trans. Vehic. Technol. 59 (2010), no. 1, 150-159. https://doi.org/10.1109/TVT.2009.2029862
  24. Y. S. Cho, J. Kim, W. Y. Yang, and C. G. Kang, MIMO-OFDM wireless communications with MATLAB(R), Wiley-IEEE Press 2010.
  25. 3GPP NR specification. http://www.3gpp.org/dynareport/38-series.htm
  26. X. Chen, S. Xie, and K. He, An empirical study of training selfsupervised vision transformers, (Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada), 2021, pp. 9640-9649.
  27. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, (Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada), 2021, pp. 10012-10022.
  28. 3rd generation partnership project; Technical Specification Group Radio Access Network; Study on channel model for frequencies from 0.5 to 100 GHz (Release 17), 2022.
  29. J.-I. Kim, J.-H. Jang, and H.-J. Choi, A low-complexity 2-D MMSE channel estimation for OFDM systems, J. Korea Inform. Commun. Soc. 36 (2011), no. 5C, 317-325.