跳到主要內容

臺灣博碩士論文加值系統

(44.192.48.196) 您好!臺灣時間:2024/06/14 17:26
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:張百荃
研究生(外文):CHANG, BAI-CHUAN
論文名稱:第五代行動通訊開放架構基站之高可靠低延遲通信會話管理: 使用機器學習方法
論文名稱(外文):Session Management for URLLC in 5G Open-RAN: A Machine-Learning Based Approach
指導教授:連紹宇
指導教授(外文):LIEN, SHAO-YU
口試委員:杜永枰蔡華龍李皇辰
口試委員(外文):TU, YUNG-PINGTSAI, HUA-LUNGLEE, HUANG-CHEN
口試日期:2020-07-29
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:97
中文關鍵詞:增強型移動寬頻高可靠低延遲通信巨量多機器型態通訊第三代合作夥伴計畫用戶設備無線接取網路增強式學習開放架構基站
外文關鍵詞:eMBBURLLCmMTC3GPPUERANReinforcement LearningOpen-RAN
相關次數:
  • 被引用被引用:1
  • 點閱點閱:623
  • 評分評分:
  • 下載下載:103
  • 收藏至我的研究室書目清單書目收藏:0
在International Mobile Telecommunications-2020 (IMT-2020)規範中訂立了第五代行動通訊系統的三大需求,分別是Enhanced Mobile Broadband (eMBB)、 Ultra Reliable and Low Latency Communication (URLLC) 和Massive Machine Type Communications (mMTC),而隨著第五代行動通訊系統的發展,第三代合作夥伴計畫提出了依照IMT-2020規範而建立的第五代行動通訊新無線電。而其中對於URLLC是要求其單一封包延遲需小於等於一毫秒,但由於該延遲在整個第五代行動通訊系統中並非源自單一來源,例如用戶設備要傳送單一封包至電腦網路的服務提供者,其延遲便可能來自由用戶設備至基站的空中接口、基站至核心網路的傳輸時間等。對於基站而言,如果對於正在服務的URLLC用戶設備因為偶發一些網路問題而沒有辦法滿足其需求,該用戶設備若等待上層網路將其線路切換至符合其需求的等待時間,會使得延遲大量增加。若能夠使基站對各種用戶設備的會話需求以及線路是否穩定等資料記錄下來,使用機器學習方法讓基站能夠自行決定是允許建立該會話需求,以避免建立會話後造成無法接受的封包延遲。由於現行的基站架構不能支援機器學習的功能,在本論文中因而提出基於開放架構基站的會話管理方法,並建立機器學習的功能。本論文進一步評估基於不同增強式學習演算法會話管理方法之效能,其結果顯示所提出方法能有效避免所建立之會話其服務需求無法被滿足的狀況。
The International Mobile Telecommunications-2020 (IMT-2020) defines that the 5G system should support Enhanced Mobile Broadband (eMBB), Ultra Reliable and Low Latency Communication (URLLC), and Massive Machine Type Communications (mMTC). With the implementation of fifth generation mobile communication system (5G system), the 3rd Generation Partnership Project (3GPP) had proposed the 5G New Radio (NR) specification which followed with the IMT-2020. For the URLLC, the latency should be lower or equal to 1 millisecond. Since the latency does not obtain from single source. For example, when a packet transmits from a User Equipment (UE) to the service provider. The latency could be obtained from the air interface between the UE and the base station, between the base station and the Core Network, and between the Core Network and the destination of this packet. To the base station, if the base station cannot comply the requirements with the serving URLLC UE since some occasionally network problem. In this situation, although the session cannot comply with the requirements, the UE still needs to transmit the packet through the original session until the Core Network switching the UE’s path. The waiting time of switching procedure cause massive latency. If the base station can record the information of the UE’s session requirements, UE's session is stable or not, etc., to allow the base station to determine to accept the request of session establishment or not by using Machine Learning method, so as to avoid unacceptable packet latency after the session is established. Since the current base station architecture cannot support the function of Machine Learning, this thesis proposes a session management method based on Open-RAN and establishes the function of Machine Learning. This thesis further evaluates the performance of session management method based on different Reinforcement Learning algorithms. The result show that the proposed method can effectively avoid the situation where the service requirements of established sessions cannot be met.
1 中文摘要 3
2 Abstract 4
3 Introduction 5
3.1 Latency in 5G system 5
3.2 Session Management 7
3.3 Machine Learning Methods 9
3.4 Architecture of Open-RAN 10
3.5 RAN Simulator with Session Management Method 12
4 Session Management Method with Reinforcement Learning 13
4.1 TD Methods 14
4.2 Session Management Method 16
5 RAN Simulator 19
5.1 NG-RAN Architecture 20
5.1.1 NG Interface Protocol Stack 20
5.1.1.1 NG Control Plane 21
5.1.1.2 NG User Plane 22
5.1.2 Radio Protocol Architecture 22
5.1.3 RAN Simulator Architecture 22
5.1.4 RAN Simulator Interface 23
5.2 gNB Registration Procedure to Core Network 23
5.3 UE Simulator 24
5.3.1 NAS Protocol 25
5.3.2 UE Simulator Architecture 26
5.3.3 UE Attachment Procedure to Core Network 26
5.3.3.1 Registration Procedure 27
5.3.3.2 Authentication Procedure 28
5.3.3.3 Security Mode 29
5.3.3.4 PDU Session Establishment Procedure 30
5.3.3.5 UE Context Setup Within gNB 31
5.4 Other Procedure RAN Simulator Support 32
5.4.1 UE Context Release 32
5.4.2 Path Switch 32
5.4.3 PDU Session Management 33
5.4.4 Handover 33
6 Performance Evaluation 35
7 Conclusion 93
8 Reference 95


[ 1 ] Imtiaz Parvez, Ali Rahmati, Ismail Guvenc, Arif I. Sarwat, Huaiyu Dai, “A Survey on Low Latency Towards 5G: RAN, Core Network and Caching Solutions”, IEEE Communications Surveys & Tutorials, 2018.
[ 2 ] ITU-R Recommendation ITU-R M.2083-0, “IMT Vision – Framework and overall objectives of the future development of IMT for 2020 and beyond”, 09/2015
[ 3 ] Cesar A. Garcia-Perez, Pedro Merino, “Enabling Low Latency Services on LTE Networks”, 2016 IEEE 1st International Workshops on Foundations and Applications of Self Systems (FASW)
[ 4 ] Cristina -Gabriela Gheorghe, Dan Alexandru Stoichescu, Radu Dragomir, “Latency requirement for 5G mobile communications”, 2018 10th International Conference on Electronics, Computers and Artificial Intelligence (ECAI).
[ 5 ] Mona Jaber, Muhammad Ali Imran, Rahim Tafazolli, Anvar Tukmanov, “5G Backhaul Challenges and Emerging Research Directions: A Survey”, IEEE Access, 2016.
[ 6 ] Benzekki, Kamal; El Fergougui, Abdeslam; Elbelrhiti Elalaoui, Abdelbaki, "Software-defined networking (SDN): A survey", Security and Communication Networks, 2016.
[ 7 ] ETSI GS NFV 001 version 1.1.1, “Network Functions Virtualisation (NFV), Use Cases”, 2013.
[ 8 ] 3GPP TS 23.501 version 15.2.0 Release 15, “System Architecture for the 5G System”, 2018
[ 9 ] 3GPP TS 29.500 version 15.0.0 Release 15, “5G System, Technical Realization of Service Based Architecture, Stage 3”, 2018
[ 10 ] Truong-Xuan Do, Younghan Kim, “Latency-aware Placement for State Management Functions in Service-based 5G Mobile Core Network”, 2018 IEEE Seventh International Conference on Communications and Electronics (ICCE).
[ 11 ] G. Pocovi, K. I. Pedersen, B. Soret, M. Lauridsen, P. Mogensen, “On the impact of multi-user traffic dynamics on low latency communications”, IEEE Int. Symp. Wireless Commun. Syst. ISWCS), 2016
[ 12 ] Guillermo Pocovi, Klaus I. Pedersen, Beatriz Soret, Mads Lauridsen, Preben Mogensen,” On the impact of multi-user traffic dynamics on low latency communications”, 2016 International Symposium on Wireless Communication Systems (ISWCS)
[ 13 ] Byungju Lee, Sunho Park, David J. Love, Hyoungju Ji, Byonghyo Shim, “Packet Structure and Receiver Design for Low Latency Wireless Communications With Ultra-Short Packets”, IEEE Transactions on Communications, 2018
[ 14 ] R. Jin, X. Zhong, and S. Zhou, “The access procedure design for low latency in 5G cellular network”, IEEE Globecom Workshop (GC Wkshps), Washington, DC, 2016
[ 15 ] J. Zhang, X. Zhang, and W. Wang, “Cache-enabled software defined heterogeneous networks for green and flexible 5G networks”, IEEE Access, vol. 4, 2016
[ 16 ] R. J. Weiler et al, “Enabling 5G backhaul and access with millimeterwaves”, IEEE Eur. Conf. Netw. Commun. (EuCNC), 2014
[ 17 ] Kyoungjae Sun, Younghan Kim, “PMIP-Based Distributed Session Mobility Management for 5G Mobile Network”, 2019 International Conference on Information Networking.
[ 18 ] Ronit Nossenson, Noam Amram, “Session management in a multi-channel video streaming system for wireless networks”, 2012 18th IEEE International Conference on Networks.
[ 19 ] 3GPP TS 23.502 version 15.2.0 Release 15, “Procedures for the 5G System”, 2018
[ 20 ] 3GPP TS 38.300 version 15.3.1 Release 15, “5G, NR, Overall description, Stage-2”, 2018
[ 21 ] Meng-Chun Hou, “Optimally Autonomous Multiple Aerial Base Stations Deployment for UAV Networks: Reinforcement Learning Approaches”, 2020.
[ 22 ] O-RAN-WG1-O-RAN Architecture Description - v01.00.00, “O-RAN Architecture Description” ,2020.
[ 23 ] https://www.free5gc.org/, “free5GC”.
[ 24 ] Richard S. Sutton, Andrew G. Barto, “Reinforcement Learning: An Introduction, Second edition”, 2017
[ 25 ] https://www.ubuntu-tw.org/, “Ubuntu OS”.
[ 26 ] 3GPP TS 24.501 version 15.0.0 Release 15, “5G, Non-Access-Stratum (NAS) protocol for 5G System (5GS), Stage 3”, 2018.
[ 27 ] 3GPP TS 38.413 version 15.0.0 Release 15, “5G, NG-RAN, NG Application Protocol (NGAP)”, 2018.
[ 28 ] 3GPP TS 24.501 version 15.0.0 Release 15, “5G, Non-Access-Stratum (NAS) protocol for 5G System (5GS), Stage 3”, 2018
[ 29 ] 3GPP TS 38.401 version 15.5.0 Release 15, “5G, NG-RAN, Architecture description”, 2019

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊