機器學習無線通訊
Machine Learning for Wireless Communications
| 節 | 週三 |
|---|---|
A 18:30–19:20 | 機器學習無線通訊 ED203 3 節連堂 |
B 19:30–20:20 | |
C 20:30–21:20 |
* 根據陽明交大上課時間表所列
This course aims to equip students with machine learning (AI) and wireless communication algorithm design capabilities, understanding 5G and O-RAN architectures, and enabling hands-on implementation of communication algorithms in 5G and O-RAN small base stations on FPGA/RFSoC platforms. Students will learn the complete process from communication system modeling and AI algorithm design to implementation and testing on an FPGA board, thereby mastering cross-domain skills spanning theory, algorithms, and hardware implementation. Course objectives include: Part I: Wireless Communication Fundamentals and Communication Algorithm Design (王蒞君老師、闕河鳴老師): Master the fundamentals of communication OFDM, gain familiarity with the Vivado/Vitis development process, and be able to convert algorithms into RTL. Part II: FPGA/RFSoC Platform Implementation (陳達慶老師、王蒞君老師): Combine software-defined radio (SDR) with FPGA acceleration and implement them on an RFSoC hardware platform. Part III: Communications AI Chip Introduction and Design (闕河鳴老師、王蒞君老師): Learn machine learning and real-time AI algorithm techniques and apply them to communications chips. Part IV: 5G ORAN (許亨仰老師、王蒞君老師): Decomposing the traditional closed 5G base station functions into three independent units: the radio unit (RU), the distributed unit (DU), and the centralized unit (CU).
1. Digital Communications 2. Computer Networks
1. Assignments: 20% 2. Mid-Term: 30% 3. Final Exam 30% 4. Project 20%
| 週次 | 主題 |
|---|---|
| 第 1 週 | - Course Introduction- Vivado / Vitis Introduction Overview + RFSoC FPGA (Summer 課程成果) AMD FPGA Architecture & Design Flow Development Tools and Environment |
| 第 2 週 | - OFDM Transmitter Design OFDM Modulation & Frame Generation RFDC Configuration & IP Integration |
| 第 3 週 | - OFDM Transmitter Design OFDM Transmitter – RF Up-Conversion |
| 第 4 週 | - OFDM Receiver Design OFDM Receiver – RF Down-Conversion |
| 第 5 週 | - OFDM Receiver Design OFDM Receiver Synchronization |
| 第 6 週 | - OFDM Receiver Design Channel Estimation and Equalization |
| 第 7 週 | - OFDM Transmission and Receivin OFDM System Integration |
| 第 8 週 | - OFDM Transmission and Receivin OFDM System Tseting |
| 第 9 週 | Introduction and Design of Communication AI Chips (I) |
| 第 10 週 | Introduction and Design of Communication AI Chips (II) |
| 第 11 週 | - Wireless Technology Trend (1G~5G)- Wi-Fi vs Cellular- 5G feature (eMBB/URLLC/mMTC)- Cellular System Architecture 5G telecom system experiment I |
| 第 12 週 | - Radio Frame Structure- Slot configuration- 5G NR Physical Channels- Signal Processing 5G telecom system experiment II |
| 第 13 週 | - 5G NR Protocol Stack- Attach Procedure- L2 DL/UL Data Flow- RRC and NAS 5G telecom system experiment III |
| 第 14 週 | - Applications for 5G Telecommunication 5G telecom system experiment IV |
| 第 15 週 | - RedCap- NTN Telecom Type- IoT NTN- NR NTN 5G telecom system experiment V |
| 第 16 週 | Final-Term Exams: Final Presentation (Students) |
1. Machine Learning for Future Wireless Communications, F. L. Luo, Wiley, IEEE Press, 2020 2. Key Technologies for 5G Wireless Systems, Vincent W. S. Wong, Robert Schober, Derrick Wing Kwan Ng, Li-Chun Wang, Cambridge University Press 2017. 3. SDR with Zynq Ultrascale+ RFSoC, AMD, 2022. 4. Shaping future 6G networks: Needs, impacts, and technologies. John Wiley & Sons, 2021.
- 聯絡方式
- wang@nycu.edu.tw