MARL-Based Access Control for Grant-Free Non-Orthogonal Random Access in UDN
- Title
- MARL-Based Access Control for Grant-Free Non-Orthogonal Random Access in UDN
- Author
- 조성현
- Keywords
- Internet of things (IoT); Grant-free random access; umMTC; NOMA; UDN; multi-agent reinforcement learning
- Issue Date
- 2024-05-22
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Citation
- IEEE INTERNET OF THINGS JOURNAL, page. 1-16
- Abstract
- This study addresses the challenge of high power collision rates in Grant-Free Non-Orthogonal Random Access (GF-NORA) for ultra-massive machine-type communication (umMTC) in ultra-dense networks (UDN). We analyze the impact of power collision and inter-cell interference, defining the key factors affecting successive interference cancellation (SIC) decoding failure. To tackle power collision problem, we propose a multi-agent reinforcement learning (MARL) framework, QMIX algorithm, with joint optimization of access control and power-level design. We evaluate the performance of the proposed scheme with extensive random access simulations in an umMTC environment. Our approach outperforms state-of-the-art schemes, achieving at most 10% increase in successful SIC decoding rate with lower access delay.
- URI
- https://ieeexplore.ieee.org/document/10537046https://repository.hanyang.ac.kr/handle/20.500.11754/190919
- ISSN
- 2327-4662
- DOI
- 10.1109/JIOT.2024.3404418
- Appears in Collections:
- COLLEGE OF COMPUTING[E](소프트웨어융합대학) > COMPUTER SCIENCE(소프트웨어학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML