毫米波 (mmWave) 通訊因其在高頻下的巨大頻寬而獲得了極大的研究關注，並且是期望應用在在下一代無線通訊網絡的關鍵技術。為了克服毫米波傳輸時遭受的嚴重路徑損耗，通常採用具有大天線陣列的波束成形技術來獲得高方向性波束和高天線增益。
要獲得高方向性波束與高天線增益，系統需仰賴於足夠準確的通道估計且會大量運用到天線，通道估計也會因為系統使用較尖細的波束，負擔十分可觀，而變得更加困難。因此，低硬體成本和低計算複雜度的基於編碼簿之波束成形技術可以有效降低系統整體負擔。
在本論文中，我們提出了一種毫米波通訊下，基於深度學習的波束選擇方法，系統使用混和波束成形。將波束選擇問題視為超解析度問題。具體而言，我們將較粗波束提供接收端的能量作為一張圖片輸入並使用深度卷積網絡來預測更細的波束，利用少量波束測量就可以預測並選擇達到最大訊雜比(SNR)的波束。模擬結果顯示，本論文所提出之方法能夠準確地估計出更細的波束，並在各種場景下以低系統負擔實現高頻譜效率。

Millimeter wave (mmWave) communication has gain enormous research attention due to its substantial bandwidth at high frequencies, and is a critical technology which expected to be employed in next generation wireless network. In order to overcome the severe path loss in mmWave communication links, beamforming techniques with large antenna array are often deployed to attain high direction beams and high antenna gain beams.
Obtaining high antenna gain from high direction beam rely on sufficient accuracy of channel estimation which make lots use of antenna, channel estimation gets much more challenging owing to the heavy training overhead using narrow beams. Hence, codebook-based beamforming can effectively improve this defect with low hardware cost and low computational complexity.
In this paper, a deep learning-based hybrid beamforming beam selection method in mmWave communication is proposed, we regard beam selection problem as super-resolution problem. To be detailed, we use deep convolutional neural networks to estimate the high resolution beams based on low resolution beam measurements, select the beam achieves the largest signal-to-noise-power-ratio (SNR) according to the output. Simulation results show that the proposed method not only estimates the beam accurately but also achieves high spectral efficiency with low overhead in various scenario.

摘要 i
Abstract ii
圖次 v
表次 vi
第一章 緒論 1
1.1 研究背景與動機 1
1.2 論文章節內容安排 4
第二章 相關背景 5
2.1 多輸入多輸出系統 5
2.2 波束成形 6
2.3 波束選擇 8
2.4 卷積神經網路 9
第三章 系統模型 12
3.1 系統架構 12
3.2 通道模型 14
3.2 波束成形與編碼簿 16
第四章 本論文提出之SR-BS模型 19
4.1 模型框架(Model Framework) 19
4.1.1 預先升採樣(Pre-upsampling) 19
4.1.2 後升採樣(Post-upsampling) 19
4.1.3 漸進升採樣(Progressive-upsampling) 20
4.2 總覽 SR-BS模型 22
4.3特徵強化區塊設計 25
第五章 模擬結果與分析 26
5.1 模擬環境與比較對象 26
5.2 訓練資料與效能指標 26
5.3 特徵強化區塊分析結果 28
5.4 SR-BS模擬結果 29
第六章 結論 38
參考文獻 39

[1] M. Agiwal, A. Roy and N. Saxena, "Next Generation 5G Wireless Networks: A Comprehensive Survey," in IEEE Communications Surveys & Tutorials, vol. 18, no. 3, pp. 1617-1655, third quarter 2016.
[2] A. Zanella, N. Bui, A. Castellani, L. Vangelista and M. Zorzi, "Internet of Things for Smart Cities," in IEEE Internet of Things Journal, vol. 1, no. 1, pp. 22-32, Feb. 2014.
[3] L. Zheng, "5g mobile communication development trend and several key technologies, " in Matec Web of Conferences, vol. 246, Jan. 2018, p. 3034.
[4] 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," in IEEE Journal of Selected Topics in Signal Processing, vol. 10, no. 3, pp. 436-453, April 2016.
[5] D. J. Love and R. W. Heath, "Limited feedback unitary precoding for spatial multiplexing systems," in IEEE Transactions on Information Theory, vol. 51, no. 8, pp. 2967-2976, Aug. 2005.
[6] H. Huang, Y. Song, J. Yang, G. Gui and F. Adachi, "Deep-Learning-Based Millimeter-Wave Massive MIMO for Hybrid Precoding," in IEEE Transactions on Vehicular Technology, vol. 68, no. 3, pp. 3027-3032, March 2019.
[7] C. Wen, W. Shih and S. Jin, "Deep Learning for Massive MIMO CSI Feedback," in IEEE Wireless Communications Letters, vol. 7, no. 5, pp. 748-751, Oct. 2018.

[8] A. Ali, N. González-Prelcic and R. W. Heath, "Millimeter Wave Beam-Selection Using Out-of-Band Spatial Information," in IEEE Transactions on Wireless Communications, vol. 17, no. 2, pp. 1038-1052, Feb. 2018.
[9] W. U. Bajwa, J. Haupt, A. M. Sayeed and R. Nowak, "Compressed Channel Sensing: A New Approach to Estimating Sparse Multipath Channels," in Proceedings of the IEEE, vol. 98, no. 6, pp. 1058-1076, June 2010.
[10] Z. Xiao, T. He, P. Xia and X. Xia, "Hierarchical Codebook Design for Beamforming Training in Millimeter-Wave Communication," in IEEE Transactions on Wireless Communications, vol. 15, no. 5, pp. 3380-3392, May 2016.
[11] S. Kutty and D. Sen, "An improved numerical optimization method for efficient beam search in 60 GHz indoor millimeter wave wireless networks," 2015 IEEE International Conference on Advanced Networks and Telecommuncations Systems ANTS), 2015, pp. 1-6.
[12] G. Gui, H. Huang, Y. Song and H. Sari, "Deep Learning for an Effective Nonorthogonal Multiple Access Scheme," in IEEE Transactions on Vehicular Technology, vol. 67, no. 9, pp. 8440-8450, Sept. 2018.
[13] M. S. Sim, Y. Lim, S. H. Park, L. Dai and C. Chae, "Deep Learning-Based mmWave Beam Selection for 5G NR/6G With Sub-6 GHz Channel Information: Algorithms and Prototype Validation," in IEEE Access, vol. 8, pp. 51634-51646, 2020.
[14] A. Klautau, P. Batista, N. González-Prelcic, Y. Wang and R. W. Heath, "5G MIMO Data for Machine Learning: Application to Beam-Selection Using Deep Learning," 2018 Information Theory and Applications Workshop ITA), 2018.
[15] A. Klautau, N. González-Prelcic and R. W. Heath, "LIDAR Data for Deep Learning-Based mmWave Beam-Selection," in IEEE Wireless Communications Letters, vol. 8, no. 3, pp. 909-912, June 2019.
[16] Z. Wang, J. Chen and S. C. H. Hoi, "Deep Learning for Image Super-resolution: A Survey," in IEEE Transactions on Pattern Analysis and Machine Intelligence.
[17] W. Lai, J. Huang, N. Ahuja and M. Yang, "Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 11, pp. 2599-2613, 1 Nov. 2019
[18] M. Giordani, M. Mezzavilla, C. N. Barati, S. Rangan and M. Zorzi, "Comparative analysis of initial access techniques in 5G mmWave cellular networks," 2016 Annual Conference on Information Science and Systems (CISS), 2016, pp. 268-273.
[19] C. Lin, W. Kao, S. Zhan and T. Lee, "BsNet: A Deep Learning-Based Beam Selection Method for mmWave Communications," 2019 IEEE 90th Vehicular Technology Conference VTC2019-Fall), 2019, pp. 1-6.
[20] H. Echigo, Y. Cao, M. Bouazizi and T. Ohtsuki, "A Deep Learning-Based Low Overhead Beam Selection in mmWave Communications," in IEEE Transactions on Vehicular Technology, vol. 70, no. 1, pp. 682-691, Jan. 2021.
[21] Remcom, Wireless insite. [online] Available:http://www.remcom.com/wireless-insite.
[22] C. Antón-Haro and X. Mestre, "Learning and Data-Driven Beam Selection for mmWave Communications: An Angle of Arrival-Based Approach," in IEEE Access, vol. 7, pp. 20404-20415, 2019.
[23] S. Noh, M. D. Zoltowski and D. J. Love, "Multi-Resolution Codebook and Adaptive Beamforming Sequence Design for Millimeter Wave Beam Alignment," in IEEE Transactions on Wireless Communications, vol. 16, no. 9, pp. 5689-5701, Sept. 2017.
[24] J. Butler and R. Lowe, "Beamforming matrix simplifies design of electrically scanned antennas", Electron. Design, vol. 9, no. 4, pp. 170-173, Apr. 1961.
[25] Z. Wang, J. Chen and S. C. H. Hoi, "Deep Learning for Image Super-resolution: A Survey," in IEEE Transactions on Pattern Analysis and Machine Intelligence.
[26] Y. Tai, J. Yang and X. Liu, "Image Super-Resolution via Deep Recursive Residual Network," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[27] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016.
[28] J. Yosinski, J. Clune, Y. Bengio and H. Lipson, "How transferable are features in deep neural networks", Advances in Neural Information Processing Systems, pp. 3320-3328, 2014.
[29] S. Kutty and D. Sen, "An improved numerical optimization method for efficient beam search in 60 GHz indoor millimeter wave wireless networks," 2015 IEEE International Conference on Advanced Networks and Telecommuncations Systems (ANTS), 2015.
[30] W. Kao, S. Zhan and T. Lee, "AI-Aided 3-D Beamforming for Millimeter Wave Communications," 2018 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2018.
[31] C. Lin, W. Kao, S. Zhan and T. Lee, "BsNet: A Deep Learning-Based Beam Selection Method for mmWave Communications," 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), 2019, pp. 1-6.