DC 欄位 |
值 |
語言 |
DC.contributor | 通訊工程學系 | zh_TW |
DC.creator | 王星月 | zh_TW |
DC.creator | Xing-Yue Wang | en_US |
dc.date.accessioned | 2023-8-1T07:39:07Z | |
dc.date.available | 2023-8-1T07:39:07Z | |
dc.date.issued | 2023 | |
dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=110523601 | |
dc.contributor.department | 通訊工程學系 | zh_TW |
DC.description | 國立中央大學 | zh_TW |
DC.description | National Central University | en_US |
dc.description.abstract | 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。 | zh_TW |
dc.description.abstract | 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. | en_US |
DC.subject | 無細胞多輸入多輸出系統 | zh_TW |
DC.subject | 用戶選擇 | zh_TW |
DC.subject | 功率分配 | zh_TW |
DC.subject | 深度強化學習 | zh_TW |
DC.subject | 混合波束成形 | zh_TW |
DC.subject | 多用户检测 | zh_TW |
DC.subject | 毫米波 | zh_TW |
DC.subject | Cell-free MIMO | en_US |
DC.subject | User selection | en_US |
DC.subject | Power Allocation | en_US |
DC.subject | Deep Reinforcement Learning | en_US |
DC.subject | Hybrid Beamforming | en_US |
DC.subject | Multiuser detection | en_US |
DC.subject | Millimeter-Wave | en_US |
DC.title | 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 | zh_TW |
dc.language.iso | zh-TW | zh-TW |
DC.title | Performance Study of Cell-free Massive MIMO Systems with Hybrid Precoding Based on DDPG Machine Learning | en_US |
DC.type | 博碩士論文 | zh_TW |
DC.type | thesis | en_US |
DC.publisher | National Central University | en_US |