DC 欄位 |
值 |
語言 |
DC.contributor | 通訊工程學系 | zh_TW |
DC.creator | 林奕頡 | zh_TW |
DC.creator | YI-JIE LIN | en_US |
dc.date.accessioned | 2024-8-19T07:39:07Z | |
dc.date.available | 2024-8-19T07:39:07Z | |
dc.date.issued | 2024 | |
dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=109523048 | |
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 | 本研究針對未來B5G(Beyond 5G)O-RAN(Open Radio Access Network)架構下的IIoT(Industrial Internet of Things)場域,提出了一種自適應的MTC(Machine Type Communication)封包聚合方法。隨著5G 技術的快速發展,IIoT 應用的需求不斷增加,現有網絡架構難以滿足這些多樣化需求。O-RAN 架構旨在打破傳統RAN 的封閉性,提供一個開放、靈活和可編程的網絡環境,以促進創新和降低成本。本研究首先介紹了5G 網絡中的IIoT 場域應用需求,並探討了O-RAN 架構的基本原理及其優勢。接著,基於M/G/1 排隊模型,我們描述了MTC 封包的聚合過程,並量化了此過程對O-RAN網絡效能的影響。此外,本文提出了一種基於深度強化學習(DQN, Deep Q-Network)的自適應聚合方法,該方法能夠在O-RAN 的RIC(RAN Intelligent Controller)中實現實時的網絡效能調整,從而提升網絡的使用效率並降低封包遺失率。實驗結果顯示,所提出的方法在不同的網絡環境下均能顯著提高封包傳輸效率和網絡吞吐量,並有效 降低封包遺失率。本研究的主要貢獻在於設計了一個適用於B5G O-RAN IIoT 場域的可調性MTC 封包聚合方法,並驗證了其在提升網絡效能方面的有效性 | zh_TW |
dc.description.abstract | This study proposes an adaptive MTC (Machine Type Communication) packet aggregation method suitable for B5G (Beyond 5G) O-RAN (Open Radio Access Network) architectures in IIoT (Industrial Internet of Things) fields. With the rapid development of 5G technology, the demand for IIoT applications continues to increase, and existing network architectures struggle to meet these diverse needs. The O-RAN architecture aims to break the closed nature of traditional RANs, providing an open, flexible, and programmable network environment to foster innovation and reduce costs.The study first introduces the application requirements of IIoT fields in 5Gnetworks and explores the basic principles and advantages of the O-RAN architecture. Then,based on the M/G/1 queuing model, we describe the MTC packet aggregation process and quantify its impact on the performance of O-RAN networks. Furthermore, this paper proposes an adaptive aggregation method based on Deep Q-Network (DQN), which can achieve real-time network performance adjustments in the RIC (RAN Intelligent Controller) of O-RAN, thereby enhancing network efficiency and reducing packet loss rates.Experimental results show that the proposed method significantly improves packet transmission efficiency and network throughput in various network environments while effectively reducing packet loss rates. The main contribution of this study lies in designing a scalable MTC packet aggregation method suitable for B5G O-RAN IIoT fields and verifying its effectiveness in improving network performance. | en_US |
DC.subject | B5G | zh_TW |
DC.subject | O-RAN | zh_TW |
DC.subject | 封包聚合 | zh_TW |
DC.subject | 深度強化學習 | zh_TW |
DC.subject | DQN | zh_TW |
DC.subject | 網絡效能 | zh_TW |
DC.subject | 工業物聯網 | zh_TW |
DC.subject | 自適應聚合方法 | zh_TW |
DC.subject | Beyond 5G | en_US |
DC.subject | Open Radio Access Network | en_US |
DC.subject | Packet Aggregation | en_US |
DC.subject | Deep Reinforcement Learning | en_US |
DC.subject | Deep Q-Network | en_US |
DC.subject | Network Performance | en_US |
DC.subject | Industrial Internet of Things (IIoT) | en_US |
DC.subject | Adaptive Aggregation Method | en_US |
DC.title | 適用於B5G O-RAN IIoT 場域之可調性MTC 封包 聚合方法 | zh_TW |
dc.language.iso | zh-TW | zh-TW |
DC.title | Adaptive MTC Packet Aggregation Method in B5G O-RAN IIoT Fields | en_US |
DC.type | 博碩士論文 | zh_TW |
DC.type | thesis | en_US |
DC.publisher | National Central University | en_US |