毫米波頻譜因可容納持續成長的資料流量，已受到未來無線通訊相關學者專家的高度關注；然而，毫米波通訊存在顯著的訊號衰減問題，也因此準確的通道估測與追蹤並不易達成，具有高度挑戰性。在本論文中，我們針對下行毫米波混合波束成形系統，提出一種基於深度學習的波束追蹤方案，其中射頻鏈與天線間採用部分連接結構，以降低硬體複雜度，亦即每一個射頻鏈僅連接到一個子天線陣列；所發展的深度學習方案依據雙向有序神經元長短期記憶 (bidirectional ordered neurons long short-term memory；縮寫為Bi-ONLSTM) 模型設計，以更精確地萃取資料特徵，進而增強學習能力，其中Bi-ONLSTM基本處理單元乃由傳統的LSTM基本單元加上主遺忘閥 (master forget gates) 與主輸入閥 (master input gates) 而成。與LSTM結構相比，Bi-ONLSTM並未顯著增加運算複雜度；廣泛的電腦模擬結果亦顯示，在各種不同的用戶設備速度情況下，所提出之Bi-ONLSTM波束追蹤方案比現有的卡爾曼濾波和LSTM相關作法具有明顯較佳的正規化通道均方誤差效能。

The millimeter wave (mmWave) frequency spectrum has received great attention for future wireless communications to accommodate the continuous growth in data traffic. Since there is significant signal attenuation in mmWave communications, it is challengeable to achieve accurate channel estimation and tracking. In this thesis, a beam-tracking scheme based on deep learning (DL) is proposed for downlink mmWave hybrid beamforming systems, which employ a partially connected structure with each radio-frequency chain connected to only a subarray of antennas to reduce hardware complexity. The DL scheme is designed by using the bidirectional ordered neurons long short-term memory (Bi-ONLSTM) model, where the basic is formed by adding master forget gates and master input gates to the basic cell of traditional LSTM models for extracting data features more precisely as well as enhancing the learning performance. As compared with LSTM structures, Bi-ONLSTM does not have a significant increase in the computational complexity. Extensive computer simulation results also show that the proposed Bi-ONLSTM beam-tracking scheme provides obviously better performance, in terms of the normalized channel mean-squared error, than existing Kalman filtering and LSTM approaches for various velocities of user equipment.

[1] T. S. Rappaport et al., “Millimeter wave mobile communications for 5G cellular: It will work!” IEEE Access, vol. 1, pp. 335–349, May 2013.
[2] A. M. Al-Samman, M. H. Azmi, and T. A. Rahman, “A survey of millimeter wave (mm-Wave) communications for 5G: Channel measurement below and above 6 GHz,” in Proc. 3rd Int. Conf. Reliable Inf. Commun. Technol. Springer, 2018, pp. 451–463.
[3] R. W. Heath, Jr., N. Gonzalez-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.
[4] L. Liu and H. Jafarkhani, “Space-time trellis codes based on channel-phase feedback,” IEEE Trans. Commun., vol. 54, no. 12, pp. 2186–2198, Dec. 2006.
[5] A. Hottinen, O. Tirkkonen, and R. Wichman, Multi-antenna transceiver techniques for 3G and beyond. John Wiley & Sons, Aug. 2004.
[6] A. Narula, M. J. Lopez, M. D. Trott, and G. W. Wornell, “Efficient use of side information in multiple-antenna data transmission over fading channels,” IEEE J. Sel. Areas Commun., vol. 16, no. 8, pp. 1423–1436, Oct. 1998.
[7] J. H. C. van den Heuvel, J. M. G. Linnartz, P. G. M. Baltus, and D. Cabric, “Full MIMO spatial filtering approach for dynamic range reduction in wideband cognitive radios,” IEEE Trans. Circuits and Syst. I: Reg. Papers, vol. 59, no. 11, pp. 2761–2773, Nov. 2012.
[8] J. Mo and R. W. Heath, “Capacity analysis of one-bit quantized MIMO systems with transmitter channel state information,” IEEE Trans. Signal Process., vol. 63, no. 20, pp. 5498–5512, Oct. 2015.
[9] S. Jacobsson, G. Durisi, M. Coldrey, U. Gustavsson, and C. Studer, “Throughput analysis of massive MIMO uplink with low-resolution ADCs,” IEEE Trans. on Wireless Commun., vol. 16, no. 6, pp. 4038– 4051, Jun. 2017.
[10] X. Zhang, A. F. Molisch, and S.-Y. Kung, “Variable-phase-shift-based RF-baseband codesign for MIMO antenna selection,” IEEE Trans. Signal Process., vol. 53, no. 11, pp. 4091–4103, Nov. 2005.
[11] W. Roh et al., “Millimeter-wave beamforming as an enabling technology for 5G cellular communications: Theoretical feasibility and prototype results,” IEEE Commun. Mag., vol. 52, no. 2, pp. 106–113, Feb. 2014.
[12] O. El Ayach, S. Rajagopal, S. Abu-Surra, Z. Pi, and R. W. Heath, Jr., “Spatially sparse precoding in millimeter wave MIMO systems,” IEEE Trans. Wireless Commun., vol. 13, no. 3, pp. 1499–1513, Mar. 2014.
[13] S. Han, C.-L. I, Z. Xu, and C. Rowell, “Large-scale antenna systems with hybrid precoding analog and digital beamforming for millimeter wave 5G,” IEEE Commun. Mag., vol. 53, no. 1, pp. 186–194, Jan. 2015.
[14] J. Singh and S. Ramakrishna, “On the feasibility of codebook-based beamforming in millimeter wave systems with multiple antenna arrays,” IEEE Trans. Wireless Commun., vol. 14, no. 5, pp. 2670–2683, May 2015.
[15] N. Li, Z. Wei, H. Yang, X. Zhang, and D. Yang, “Hybrid precoding for mmwave massive mimo systems with partially connected structure,” IEEE Access, vol. 5, pp. 15 142–15 151, 2017.
[16] C . Zhang, D. Guo and P. Fan, “Tracking angles of departure and arrival in a mobile millimeter wave channel,” in Proc. IEEE Int. Conf. Commun. (ICC) , Kuala Lumpur, Malaysia, 2016, pp. 1-6.
[17] V. Va, H. Vikalo and R. W. Heath, “Beam tracking for mobile millimeter wave communication systems, ” in Proc. IEEE Global Conf. Signal Inf. Process. (GlobalSIP), 2016, pp. 743–747.
[18] D. Shim, C. Yang J. H. Kim et al., “Application of motion sensors for beam-tracking of mobile stations in mmWave communication systems,” Sensors, vol. 14, no. 10, 2014, pp. 19622–19638.
[19] J. Bao and H. Li, “Motion aware beam tracking in mobile millimeter wave communications: A data-driven approach,” in Proc. IEEE Int. Conf. Commun. (ICC), pp. 1–6, 2019.
[20] D. Zhu, J. Choi and R. W. Heath, “Auxiliary beam pair enabled AoD and AoA estimation in closed-loop large-scale millimeter-wave MIMO systems,” IEEE Wireless Commun. Lett., vol. 16, no. 7, Jul. 2017, pp. 4770–4785.
[21] S. Kim, G. Kwon and H. Park, “Q-learning-based low complexity beam tracking for mmWave beamforming system,” in Proc. 2020 Int. Conf. Inf. Commun. Technol. Convergence (ICTC), pp. 1451– 1455, 2020.
[22] J. Jeong, S. H. Lim, Y. Song et al., “Online learning for joint beam tracking and pattern optimization in massive MIMO systems,” in Proc. IEEE Conf. Compu. Commun. (INFOCOM), pp. 764–773, 2020.
[23] R. Wang, P. V. Klaine, O. Onireti, Y. Sun, M. A. Imran and L. Zhang, “Deep learning enabled beam tracking for non-line of sight millimeter wave communications,” IEEE Open J. Commun. Soc., vol. 2, pp. 1710-1720, 2021.
[24] Y. Guo, Z. Wang, M. Li and Q. Liu, “Machine learning based mmWave channel tracking in vehicular scenario,” in Proc. IEEE Int. Conf. Commun. (ICC), Shanghai, China, 2019, pp. 1-6.
[25] R. Deng, S. Chen, S. Zhou et al., “Channel fingerprint based beam tracking for millimeter wave communications,” IEEE Commun. Lett., vol. 24, no. 3, Mar. 2020, pp. 639–643.
[26] Y. Shen, S. Tan, A. Sordoni, and A. Courville, “Ordered neurons: Integrating tree structures into recurrent neural networks,” in Proc. Int. Conf. Learn. Represent. (ICLR), New Orleans, LA, USA, May 2019, pp. 1-14.
[27] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673–2681, Nov. 1997.
[28] Z. Cui, R. Ke, and Y. Wang, “Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction,” in Proc. 6th Int. Workshop Urban Comput. (UrbComp), Halifax, Canada, Aug. 2017, pp. 1–11.
[29] A. Graves and J. Schmidhuber, “Framewise phoneme classification with bidirectional LSTM and other neural network architectures,” Neural Netw., vol. 18, no. 5–6, pp. 602–610, Jul.–Aug. 2005.
[30] Q. Duan, T. Kim, H. Huang, K. Liu and G. Wang, “AoD and AoA tracking with directional sounding beam design for millimeter wave MIMO systems,” in Proc. IEEE 26th Int. Symp. Pers., Indoor Mobile Radio Commun. (PIMRC), Hong Kong, China, 2015, pp. 2271-2276.
[31] S. Shaham, M. Ding, M. Kokshoorn, Z. Lin, S. Dang and R. Abbas, “Fast channel estimation and beam tracking for millimeter wave vehicular communications,” IEEE Access, vol. 7, pp. 141104-141118, 2019.
[32] P. Zhou, X. Fang, Y. Fang, R. He, Y. Long and G. Huang, “Beam management and self-healing for mmWave UAV mesh networks,” IEEE Trans Veh. Technol., vol. 68, no. 2, pp. 1718-1732, Feb. 2019.
[33] IEEE Standard for Information Technology—Telecommunications and Information Exchange Between Systems Local and Metropolitan Area Networks - Specific Requirements - Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications, IEEE Std 802.11-2020 (Revision of IEEE Std 802.11-2016), Dec. 2020.
[34] P. Zhou et al., “IEEE 802.11ay based mmWave WLANs: Design challenges and solutions,” IEEE Commun. Surv. Tut., vol. 20, no. 3, pp. 1654–1681, Third Quarter 2018.
[35] A. Alkhateeb, O. El Ayach, G. Leus, and R. W. Heath, Jr., “Channel estimation and hybrid precoding for millimeter wave cellular systems,” IEEE J. Sel. Topics Signal Process., vol. 8, no. 5, pp. 831–846, Oct. 2014.
[36] A. Osama, M. Elsaadany, S. I. Shams, A. M. A. Omar, U. S. Mohammed and G. Gagnon, "Hybrid Precoder Design for mmWave Massive MIMO Systems with Partially Connected Architecture," Int. Symp. Netw., Compu. and Commu. (ISNCC), Dubai, United Arab Emirates, 2021, pp. 1-6
[37] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
[38] M. Schuster and K. K. Paliwal, “Bidirectional recurrent neural networks,” IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673-2681, Nov. 1997.
[39] Z. Cui, R. Ke, and Y. Wang, “Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction,” in Proc. 6th Int. Workshop Urban Comput. (UrbComp), Halifax, Canada, Aug. 2017, pp. 1–11.
[40] A. Graves and J. Schmidhuber, “Framewise phoneme classification with bidirectional LSTM and other neural network architectures,” Neural Netw., vol. 18, no. 5–6, pp.602–610, Jul. –Aug. 2005.
[41] D. Burghal, N. A. Abbasi and A. F. Molisch, “A machine learning solution for beam tracking in mmWave systems,” in Proc. 53rd Asilomar Conf. Signals, Syst., Comput., Nov. 2019, pp. 173–177.
[42] H. Kim, S. Moon and I. Hwang, “Machine learning-based channel tracking for next-generation 5G communication system,” in Proc. Twelfth Int. Conf. Ubiquitous Future Netw. (ICUFN), Jeju Island, Korea, Republic of, 2021, pp. 267-269.
[43] NR; Physical Channels and Modulation (Release 15), 3GPP TS 38.211 V15.2.0, 2018.
[44] H. Chung, J. Kang, H. Kim, Y. M. Park and S. Kim, "Adaptive Beamwidth Control for mmWave Beam Tracking," IEEE Commun. Lett., vol. 25, no. 1, pp. 137-141, Jan. 2021.