在毫米波(millimeter wave)多輸入多輸出正交分頻多工(MIMO-OFDM)系統架構之下設計混合式波束成形(Hybrid beamforming) 時，需要考量到其效能以及運算複雜度，要達到足夠的效能同時兼具合宜的運算複雜度是一個極具挑戰的設計問題。其中，加權最小均方誤差法搭配流形最佳化(WMMSE-MO)之演算法可以提供充足的效能，然而其運算複雜度相當地高。所以，在本論文中，我們打算將深度展開(Deep unfolding)技術運用到WMMSE-MO演算法上，以此來設計出一深度展開模型。相較於原本的WMMSE-MO演算法，我們提出的深度展開模型擁有更快的收斂性並且可以達到更好的效能，此外，我們也提出一個共同設計的方法，此方法可以產生合適的初始點作為深度展開模型的輸入，透過此共同設計的方法，我們可以在更少量的迭代數目下進一步提升深度展開模型的效能。最後，經由在巨量天線MIMO-OFDM系統架構下設置不同的硬體參數(例如，射頻鏈路)以及演算法參數(例如，內外迭代數) 進行模擬，模擬結果顯示出我們的方法能夠在縮減的運算時間複雜度之下提供顯著的頻譜效益(Spectral efficiency)。

Designing hybrid beamforming transceivers in millimeter wave (mmWave)MIMO-OFDM systems with satisfactory performance and acceptable complexity is a challenging problem. The well-known weighted minimum mean square error manifold optimization (WMMSE-MO) algorithm offers desired performance but has high computational complexity. In this thesis, we propose to apply the deep unfolding technique to the WMMSE-MO algorithm. The proposed deep unfolding model yields faster convergence to better solutions as compared to the original algorithm. Additionally, we also propose the joint design method to generate the appropriate initial point as the input of the deep unfolding model. This design method can further improve the performance of the deep unfolding model within fewer iteration number. Simulation results demonstrate remarkable spectral efficiency performance with reduced computational time complexity for the proposed scheme, under different hardware (RF chains) and algorithmic (inner/outer iterations)settings for a massive MIMO-OFDM system.

摘要 ------------------------------------------------------------------i
Abstract -------------------------------------------------------------ii
誌謝 -----------------------------------------------------------------iii

Chapter 1 Introduction ---------------------------------------------1
1.1 Background and Motivations -----------------------------------1
1.2 Literature Review -----------------------------------------------3
1.3 Contribution -----------------------------------------------------5
1.4 Organization of the Thesis -------------------------------------5

Chapter 2 Technical Background -----------------------------------7
2.1 MIMO Systems --------------------------------------------------7
2.2 Hybrid Beamforming -------------------------------------------8
2.3 Deep Learning --------------------------------------------------9
2.4 Deep Unfolding ------------------------------------------------11

Chapter 3 Hybrid Beamforming Design Method ------------------13
3.1 Signal Model ---------------------------------------------------14
3.2 Problem Formulation ------------------------------------------16
3.3 The WMMSE-MO Algorithm -----------------------------------18
3.4 The Proposed Deep Unfolded WMMSE-MO Algorithm -------19
3.4.1 MO RF Precoder Block --------------------------------------20
3.4.2 WMMSE BB Precoder Block ---------------------------------22
3.4.3 MO RF Combiner Block --------------------------------------22
3.4.4 WMMSE BB Combiner and Weight Matrix Block -----------23
3.4.5 Loss Function ------------------------------------------------24
3.5 Initial Point Joint Design --------------------------------------24
3.5.1 IIG Model ----------------------------------------------------26

Chapter 4 Simulations Results and Discussion ------------------28
4.1 Simulation Environment --------------------------------------28
4.2 Training Data Generation and Parameter Setting -----------28
4.3 Performance of Deep Unfolding WMMSE-MO with
Different Number of Iterations -----------------------------------29
4.4 Performance of Deep Unfolding WMMSE-MO with
IIG Initial Point ---------------------------------------------------32
4.5 Execution Time Analysis -------------------------------------34

Chapter 5 Conclusion and Future Work -------------------------36

References --------------------------------------------------------38

[1] Z. Pi and F. Khan, “An introduction to millimeter-wave mobile broadband systems,” IEEE Commun. Mag., vol. 49, no. 6, pp. 101–107, Jun. 2011.
[2] R. W. Heath, N. González-Prelcic, S. Rangan, W. Roh, and A. M. Sayeed, “An overview of signal processing techniques for millimeter wave MIMO systems,” IEEE J. Sel. Topics Signal Process., vol. 10, no. 3, pp. 436–453, Apr. 2016.
[3] C. X. Wang, F. Haider, X. Gao, X.-H. You, Y. Yang, D. Yuan, H. M. Aggoune, H. Haas, S. Fletcher, and E. Hepsaydir, “Cellular architecture and key technologies for 5G wireless communication networks,” IEEE Commun. Mag., vol. 52, no. 2, pp. 122–130, Feb. 2014.
[4] A. F. Molisch, V. V. Ratnam, S. Han, Z. Li, S. L. H. Nguyen, L. Li, and K. Haneda, “Hybrid beamforming for massive MIMO: A survey,” IEEE Commun. Mag., vol. 55, no. 9, pp.134–141, 2017.
[5] O. E. Ayach, S. Rajagopal, S. AbuSurra, Z. Pi, and R. W. Heath, “Spatially sparse precoding in millimeter wave MIMO systems,” IEEE Trans. Wireless Commun., vol. 13, no. 3, pp. 1499–1513, Mar. 2014.
[6] F. Sohrabi and W. Yu, “Hybrid digital and analog beamforming design for large-scale antenna arrays,” IEEE J. Sel. Topics Signal Process., vol. 10, no. 3, pp. 501–513, Apr.2016.
[7] X. Bao, W. Feng, J. Zheng, and J. Li, “Deep CNN and equivalent channel based hybrid precoding for mmMave massive MIMO systems,” IEEE Access, vol. 8, pp. 19 327–19 335,2020.
[8] K. Chen, J. Yang, Q. Li, and X. Ge, “Sub-array hybrid precoding for massive MIMO systems: A CNN-based approach,” IEEE Commun. Lett., vol. 25, no. 1, pp. 191–195, Jan.2021.
[9] H. Huang, Y. Song, J. Yang, G. Gui, and F. Adachi, “Deep-learning-based millimeter-wave massive MIMO for hybrid precoding,” IEEE Trans. Veh. Technol., vol. 68, no. 3, pp. 3027–3032, Mar. 2019.
[10] A. M. Elbir and K. V. Mishra, “Joint antenna selection and hybrid beamformer design using unquantized and quantized deep learning networks,” IEEE Trans. Wireless Commun., vol. 19, no. 3, pp. 1677–1688, Mar. 2020.
[11] S. Huang, Y. Ye, and M. Xiao, “Hybrid beamforming for millimeter wave multi-user MIMO systems using learning machine,” IEEE Wireless Commun. Lett., vol. 9, no. 11, pp. 1914–1918, Nov. 2020.
[12] X. Yu, J. Shen, J. Zhang, and K. B. Letaief, “Alternating minimization algorithms for hybrid precoding in millimeter wave MIMO systems,” IEEE J. Sel. Topics Signal Process., vol. 10, no. 3, pp. 485–500, Apr. 2016.
[13] F. Sohrabi and W. Yu, “Hybrid analog and digital beamforming for mmWave OFDM large-scale antenna arrays,” IEEE J. Sel. Areas Commun., vol. 35, no. 7, pp. 1432–1443, Jul. 2017.
[14] T. Lin, J. Cong, Y. Zhu, J. Zhang, and K. Ben Letaief, “Hybrid beamforming for millimeter wave systems using the MMSE criterion,” IEEE Trans. Commun., vol. 67, no. 5, pp. 3693–3708, May 2019.
[15] X. Zhao, T. Lin, Y. Zhu, and J. Zhang, “Partially-connected
hybrid beamforming for spectral efficiency maximization via a weighted MMSE equivalence,” arXiv preprint arXiv:2010.04537, 2020.
[16] Y. Sun, Z. Gao, H. Wang, B. Shim, G. Gui, G. Mao, and F. Adachi, “Principal component analysis-based broadband hybrid precoding for millimeter-wave massive MIMO systems,” IEEE Wireless Commun. Lett., vol. 19, no. 10, pp. 6331–6346, Oct. 2020.
[17] F. Yang, J. B. Wang, M. Cheng, J. Y. Wang, M. Lin, and J. Cheng, “A partially dynamic subarrays structure for wideband mmWave MIMO systems,” IEEE Trans. Commun.,vol. 68, no. 12, pp. 7578–7592, Dec. 2020.
[18] S. Minaee, Y. Y. Boykov, F. Porikli, A. J. Plaza, N. Kehtarnavaz, and D. Terzopoulos, “Image segmentation using deep learning: A survey,” IEEE Trans. Pattern Anal. Mach. Intell., pp. 1–1, 2021.
[19] C.-H. Lin, W.-C. Kao, S.-Q. Zhan, and T.-S. Lee, “BsNet: A deep learning-based beam selection method for mmWave communications,” in 2019 IEEE 90th Vehicular Technology Conference (VTC2019Fall), 2019, pp. 1–6.
[20] C.-K.Wen, W.-T. Shih, and S. Jin, “Deep learning for massive MIMO CSI feedback,” IEEE Wireless Commun. Lett., vol. 7, no. 5, pp. 748–751, 2018.
[21] A. M. Elbir and K. Vijay Mishra, “Low-complexity limited-feedback deep hybrid beamforming for broadband massive MIMO,” in 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2020, pp. 1–5.
[22] S. Gao, P. Dong, Z. Pan, and G. Y. Li, “Deep learning based channel estimation for massive MIMO with mixed-resolution ADCs,” IEEE Commun. Lett., vol. 23, no. 11, pp. 1989–1993, 2019.
[23] K. He, Z. Wang, W. Huang, D. Deng, J. Xia, and L. Fan, “Generic deep learning-based linear detectors for MIMO systems over correlated noise environments,” IEEE Access, vol. 8, pp. 29 922–29 929, 2020.
[24] H. He, S. Jin, C. K. Wen, F. Gao, G. Y. Li, and Z. Xu, Model-driven deep learning for physical layer communications,” IEEE Wireless Commun., vol. 26, no. 5, pp. 77–83, Oct.2019.
[25] H. He, C. K. Wen, S. Jin, and G. Y. Li, “Deep learning-based
channel estimation for beamspace mmwave massive MIMO systems,” IEEE Wireless Commun. Lett., vol. 7, no. 5, pp. 852–855, Oct. 2018.
[26] H. He, C.-K. Wen, S. Jin, and G. Y. Li, “A model-driven deep learning network for MIMO detection,” in 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2018, pp. 584–588.
[27] Y. Qiang, X. Shao, and X. Chen, “A model-driven deep learning algorithm for joint activity detection and channel estimation,” IEEE Commun. Lett., vol. 24, no. 11, pp. 2508–2512, Nov. 2020.
[28] L. Pellaco, M. Bengtsson, and J. Jaldén, “Deep weighted MMSE downlink beamforming,” in ICASSP 2021 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 4915–4919.
[29] C. H. Lin, Y. T. Lee, W. H. Chung, S. C. Lin, and T. S. Lee, “Unsupervised Resnet-inspired beamforming design using deep unfolding technique,” GLOBECOM 2020 2020 IEEE Global Communications Conference, pp. 1–7, 2020.
[30] Q. Hu, Y. Cai, Q. Shi, K. Xu, G. Yu, and Z. Ding, “Iterative algorithm induced deep-unfolding neural networks: Precoding design for multiuser MIMO systems,” IEEE Trans. Wireless Commun., vol. 20, no. 2, pp. 1394–1410, Feb. 2021.
[31] Q. Hu, Y. Liu, Y. Cai, G. Yu, and Z. Ding, “Joint deep reinforcement learning and unfolding: Beam selection and precoding for mmWave multiuser MIMO with lens arrays,” arXiv preprint arXiv:2010.04537, 2021.
[32] A. Balatsoukas Stimming and C. Studer, “Deep unfolding for communications systems: A survey and some new directions,” 2019 IEEE International Workshop on Signal Processing Systems (SiPS), pp. 266–271, 2019.
[33] A. L. Maas, A. Y. Hannun, and A. Y. Ng, “Rectifier nonlinearities improve neural network acoustic models,” in ICML Workshop on Deep Learning for Audio, Speech and Language Processing, 2013.
[34] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 448–456.
[35] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” Int. Conf. Learning Representations (ICLR), 2014.
[36] K.-Y. Chen, H.-Y. Chang, R. Y. Chang, and W.-H. Chung, “Hybrid beamforming in MIMO-OFDM systems via deep unfolding,” submitted to 2021 IEEE Global Communications Conference: Wireless Communications.