基於 DDPG 機器學習的數模混合預編碼無細胞 大規模 MIMO 性能研究

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：45

、訪客IP：3.129.64.21

姓名

王星月(Xing-Yue Wang) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

基於 DDPG 機器學習的數模混合預編碼無細胞大規模 MIMO 性能研究
(Performance Study of Cell-free Massive MIMO Systems with Hybrid Precoding Based on DDPG Machine Learning)

相關論文

★ 利用手持式手機工具優化行動網路系統於特殊型活動環境	★ 穿戴裝置動態軌跡曲線演算法設計
★ 石英諧振器之電極面設計對振盪頻率擾動之溫度相依性研究	★ 股票開盤價漲跌預測
★ 感知無線電異質網路下以不完美頻譜偵測進行資源配置之探討	★ 大數量且有限天線之多輸入多輸出系統效能分析
★ 具有元學習分類權重轉移網路生成遮罩於少樣本圖像分割技術	★ 具有注意力機制之隱式表示於影像重建三維人體模型
★ 使用對抗式圖形神經網路之物件偵測張榮	★ 基於弱監督式學習可變形模型之三維人臉重建
★ 以非監督式表徵分離學習之邊緣運算裝置低延遲樂曲中人聲轉換架構	★ 基於序列至序列模型之 FMCW雷達估計人體姿勢
★ 基於多層次注意力機制之單目相機語意場景補全技術	★ 應用於3GPP WCDMA-FDD上傳鏈路系統的遞迴最小平方波束合成犛耙式接收機
★ 調適性遠時程瑞雷衰退通道預測演算法設計與性能比較	★ 智慧型天線之複合式到達方位-時間延遲估測演算法及Geo-location應用

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2026-7-28以後開放)

摘要(中)

Cell-free Massive MIMO是一種分佈式的MIMO架構，它被廣泛認為是未來無線通信，如5G和6G網絡的重要技術之一。此技術的主要概念是將大量配備的多天線的接入點（APs）分散在系統覆蓋的整個服務區域內，由中央處理器通過回程網絡連接範圍內的所有接入點，並在隨機分佈的基站天線上進行相干處理，所有的APs以此為所有用戶提供統一的優質無線服務。與傳統的蜂窩網絡設計相比，無細胞大規模MIMO系統避免了小區邊緣效應，有效地抵消了用戶之間的干擾，能夠提供更均勻且更高質量的用戶體驗。在本篇論文中，我們在高頻无细胞大规模MIMO的場景下，建模了高頻MIMO信道，並在此基礎上設計了兩種不同的數字模擬兩級的預編碼方法，探索混合波束賦形的發射模式，然後基於這個兩種預編碼計算方法，用注水和DDPG的方式來進行功率分配，最終觀察仿真結果顯示，能夠證明方法可行並有效。

摘要(英)

Cell-free Massive MIMO is a distributed MIMO architecture, which is widely considered to be one of the important technologies for future wireless communications, such as 5G and 6G networks. The main concept of this technology is to disperse a large number of multi-antenna access points (APs) in the entire service area covered by the system, and the central processor connects all the access points within the range through the backhaul network, and randomly distributes Coherent processing is performed on the base station antenna, and all APs provide unified high-quality wireless services for all users. Compared with the traditional cellular network design, the cell-free massive MIMO setup mitigates the impact of cell boundary scenarios, effectively cancels the interference between users, and can provide a more uniform and higher-quality user experience. In this paper, we modeled a high-frequency MIMO channel in a high-frequency Cell free scenario, And on this basis, two different digital and analog two-level precoding methods are designed to explore the transmission mode of hybrid beamforming, and then based on these two precoding calculation methods, water injection and DDPG are used for power allocation. The final observation of the simulation results shows that the method can be proved to be feasible and effective.

關鍵字(中)

★ 無細胞多輸入多輸出系統
★ 用戶選擇
★ 功率分配
★ 深度強化學習
★ 混合波束成形
★ 多用户检测
★ 毫米波

關鍵字(英)

★ Cell-free MIMO
★ User selection
★ Power Allocation
★ Deep Reinforcement Learning
★ Hybrid Beamforming
★ Multiuser detection
★ Millimeter-Wave

論文目次

Contents

論文摘要 i
Abstract ii
Contents iv
List of Figures vi
List of Tables vii
Chpater 1. Introduction 1
Chpater 2. System model 21
2.1 Channel model 21
2.2 Problem Modeling 24
Chpater 3. Propose Scheme 25
3.1 User-Centric Method Under AP Constraints 26
3.2 Water Filling Algorithm 28
3.3 Hybrid Beamforming weight calculation 30
3.2.1 Fixed beam selection 32
3.2.2 PE-AltMin hybrid beamforming 34
3.4 Interference Rejection Combining (IRC) 36
3.5 DDPG-based Approach 38
Chpater 4. Simulation Results 45
4.1 Scenes 45
4.2 Hyper-parameter Settings 49
4.3 Result 50
Chpater 5. Conclusion 57
Reference 58

List of Figures
Fig. 1 . Cell free massive MIMO system 4
Fig. 2 . Learning Structure of Deep Policy Gradient Methods Based on AC Framework 8
Fig. 3 .Translation: 4x4 Array Sub-AP Channel 23
Fig. 4 . Digital-analog two-stage Hybrid Beamforming 30
Fig. 5 . Cell free massive MIMO system 39
Fig. 6 . Simulation scene 46
Fig. 7 . Definition of and for outdoor UEs 47
Fig. 8 . Convergence of critic. 51
Fig. 9 . Reward of the actor network. 52
Fig. 10 . Comparison of under different power allocation methods of the same precoding method(FixAng) 53
Fig. 11 . Comparison of under different power allocation methods of the same precoding method(PE_AltMin) 54
Fig. 12 . Comparison of the average with different precoding methods combined with water-filling algorithm in a user-centric manner under different environments 55
Fig. 13 . Comparison of the average with different precoding methods combined with DDPG in different environments. 55
Fig. 14 .Average comparison of different precoding methods. 56

List of Tables
Table 1 . List of abbreviations. 17
Table 2 .List of parameters. 18
Table 3 . The parameters of scenario. 48
Table 4 . The hyper-parameters of DDPG-based structure. 49

參考文獻

Reference
[1]Rappaport, T. S., Sun, S., Mayzus, R., Zhao, H., Azar, Y. K., Wang, K., ... & Samimi, M. K. (2013). Millimeter wave mobile communications for 5G cellular: It will work!. IEEE Access, 1, 335-349.
[2]Marzetta, T. L. (2010). Noncooperative cellular wireless with unlimited numbers of base station antennas. IEEE Transactions on Wireless Communications, 9(11), 3590-3600.
[3]Bjornson, E., Ngo, H. Q., Larsson, E. G., & Marzetta, T. L. (2019). Massive MIMO in sub-6 GHz and mmWave: Physical, practical, and use-case differences. IEEE Wireless Communications, 26(2), 100-108.
[4]Ngo, H. Q., Ashikhmin, A., Yang, H., Larsson, E. G., & Marzetta, T. L. (2017). Cell-free massive MIMO versus small cells. IEEE Transactions on Wireless Communications, 16(3), 1834-1850.
[5]Nayebi, A., Wild, A., Flanagan, M., & Simeone, O. (2017). Cell-free massive MIMO systems. arXiv preprint arXiv:1701.04279.
[6]Bjornson, E., Zappone, A., Sanguinetti, L., & Hoydis, J. (2020). Making cell-free massive MIMO competitive with MMSE processing and centralized implementation. IEEE Transactions on Wireless Communications, 19(1), 77-90.
[7]Björnson, E., Hoydis, J., & Sanguinetti, L. (2017). Massive MIMO has unlimited capacity. IEEE Transactions on Wireless Communications, 17(1), 574-590.
[8]Kim, S., & Shim, B. (2021). Energy-Efficient Millimeter-Wave Cell-Free Systems Under Limited Feedback. IEEE Transactions on Communications, 69, 4067-4082.
[9]Hoydis, J., Ten Brink, S., & Debbah, M. (2011, September). Massive MIMO: How many antennas do we need?. In 2011 49th Annual Allerton conference on communication, control, and computing (Allerton) (pp. 545-550). IEEE.
[10]Ngo, H. Q., Tran, H. D., Nguyen, T. Q., Matthaiou, M., & Larsson, E. G. (2021). Cell-Free Massive MIMO: A New Approach to Wireless Networking. IEEE Communications Magazine, 59(2), 197-203.
[11]Ngo, H. Q., Larsson, E. G., & Marzetta, T. L. (2017). Energy and spectral efficiency of very large multiuser MIMO systems. IEEE Transactions on Communications, 61(4), 1436-1449.
[12]Ngo, H. Q., Matthaiou, M., & Larsson, E. G. (2021). Cell-free massive MIMO versus small cells. IEEE Transactions on Wireless Communications, 16(3), 1834-1850.
[13]Lu, Z., Wang, J., & Song, J. (2020, June). Multi-resolution CSI feedback with deep learning in massive MIMO system. In ICC 2020-2020 IEEE International Conference on Communications (ICC) (pp. 1-6). IEEE.
[14]Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
[15]Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017). Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine, 34(6), 26-38.
[16]刘全, 翟建伟, 章宗长, 钟珊, 周倩, 章鹏, & 徐进. (2018). 深度强化学习综述. 计算机学报, 41(1), 1-27.
[17]Tsitsiklis, J., & Van Roy, B. (1996). Analysis of temporal-diffference learning with function approximation. Advances in neural information processing systems, 9.
[18]Yingchang LIANG,Junjie TAN,Dusit Niyato. Overview on intelligent wireless communication technology[J]. Journal on Communications, 2020, 41(7): 1-17.
[19]Zhang, H., Yang, N., Huangfu, W., Long, K., & Leung, V. C. (2020). Power control based on deep reinforcement learning for spectrum sharing. IEEE Transactions on Wireless Communications, 19(6), 4209-4219.
[20]Xianchao ZHANG, Yao ZHAO, Haijun YE, Rui FAN. Intelligent transmit power control algorithm for the multi-user interference of wireless network[J]. Journal on Communications, 2022, 43(2): 15-21.
[21]El Ayach, O., Rajagopal, S., Abu-Surra, S., Pi, Z., & Heath, R. W. (2014). Spatially sparse precoding in millimeter wave MIMO systems. IEEE transactions on wireless communications, 13(3), 1499-1513.
[22]Alkhateeb, A., El Ayach, O., Leus, G., & Heath, R. W. (2013, February). Hybrid precoding for millimeter wave cellular systems with partial channel knowledge. In 2013 Information Theory and Applications Workshop (ITA) (pp. 1-5). IEEE.
[23]Ngo, H. Q., Larsson, E. G., & Marzetta, T. L. (2014, September). Aspects of favorable propagation in massive MIMO. In 2014 22nd European Signal Processing Conference (EUSIPCO) (pp. 76-80). IEEE.
[24]Mohammed, S. L., Alsharif, M. H., Gharghan, S. K., Khan, I., & Albreem, M. (2019). Robust hybrid beamforming scheme for millimeter-wave massive-MIMO 5G wireless networks. Symmetry, 11(11), 1424.
[25]Tse, D., & Viswanath, P. (2005). Fundamentals of wireless communication. Cambridge university press.
[26]Björnson, E., Hoydis, J., & Sanguinetti, L. (2017). Massive MIMO networks: Spectral, energy, and hardware efficiency. Foundations and Trends® in Signal Processing, 11(3-4), 154-655.
[27]Hanzo, L., Wong, C. H., & Yee, M. S. (2002). Adaptive wireless transceivers: turbo-coded, turbo-equalised and space-time coded TDMA, CDMA and OFDM systems. John Wiley & Sons.
[28]GONG, S. X., WEI, X. Z., & LI, X. (2013). Review of wideband digital channelized receivers. ACTA ELECTONICA SINICA, 41(5), 949.
[29]Larsson, E. G., Edfors, O., Tufvesson, F., & Marzetta, T. L. (2014). Massive MIMO for next generation wireless systems. IEEE Communications Magazine, 52(2), 186-195.
[30]Interdonato, G., Björnson, E., Quoc Ngo, H., Frenger, P., & Larsson, E. G. (2019). Ubiquitous cell-free massive MIMO communications. EURASIP Journal on Wireless Communications and Networking, 2019, 1-13.
[31]He, C., Li, G. Y., Zheng, F. C., & You, X. (2014, December). Energy efficiency of distributed MIMO systems. In 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP) (pp. 218-222). IEEE.
[32]Mai, T. C., Ngo, H. Q., & Duong, T. Q. (2020). Downlink spectral efficiency of cell-free massive MIMO systems with multi-antenna users. IEEE Transactions on Communications, 68(8), 4803-4815.
[33]Di ZHAO, Aihuang GUO, Chunlin SONG. Power control algorithm for cell-free massive MIMO system[J]. Systems Engineering and Electronics, 2021, 43(3): 854-860.
[34]Rappaport, T. S., Heath Jr, R. W., Daniels, R. C., & Murdock, J. N. (2015). Millimeter wave wireless communications. Pearson Education.
[35]Zhao, Y., Niemegeers, I. G., & De Groot, S. M. H. (2021). Dynamic power allocation for cell-free massive MIMO: Deep reinforcement learning methods. IEEE Access, 9, 102953-102965.
[36]Claudino, L., & Abrao, T. (2018). Efficient ZF-WF strategy for sum-rate maximization of MU-MISO cognitive radio networks. AEU-International Journal of Electronics and Communications, 84, 366-374.
[37]Marzetta, T. L. (2017). Cell-free massive MIMO versus small cells. IEEE Trans. Wirel. Commun, 16, 1834-1850.
[38]Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., ... & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971.
[39]Wang, W., Zhang, F., & Lau, V. K. (2014). Dynamic power control for delay-aware device-to-device communications. IEEE Journal on Selected Areas in Communications, 33(1), 14-27.
[40]Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
[41]Xianchao ZHANG, Yao ZHAO, Haijun YE, Rui FAN. Intelligent transmit power control algorithm for the multi-user interference of wireless network[J]. Journal on Communications, 2022, 43(2): 15-21.
[42]3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Study on channel model for frequencies from 0.5 to 100 GHz (Release 16)
[43]毫米波無細胞大規模多輸入多輸出系統中使用深度強化學習技術應用於用戶選擇及功率分配[D]. National Central University, 2022.

指導教授

陳永芳(Yung-Fang Chen)

審核日期

2023-8-1

推文