Reference : Q-Learning-Based SCMA for Efficient Random Access in mMTC Networks With Short Packets
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Electrical & electronics engineering
Security, Reliability and Trust
http://hdl.handle.net/10993/47796
Q-Learning-Based SCMA for Efficient Random Access in mMTC Networks With Short Packets
English
Tran, Duc Dung mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom >]
Sharma, Shree Krishna mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom]
Chatzinotas, Symeon mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom >]
Woungang, Isaac [Ryerson University > Department of Computer Science]
Sep-2021
Proceedings of 2021 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (IEEE PIMRC 2021)
1-5
Yes
No
International
2021 IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (IEEE PIMRC 2021)
from 13-09-2021 to 16-09-2021
IEEE
Virtual Conference
[en] mMTC ; SCMA ; Q-Learning ; short-packet communications
[en] In massive machine-type communications (mMTC) networks, the ever-growing number of MTC devices and the limited radio resources have caused a severe problem of random access channel (RACH) congestion. To mitigate this issue, several potential multiple access (MA) mechanisms including sparse code MA (SCMA) have been proposed. Besides, the short-packet transmission feature of MTC devices requires the design of new transmission and congestion avoidance techniques as the existing techniques based on the assumption of infinite data-packet length may not be suitable for mMTC networks. Therefore, it is important to find novel solutions to address RACH congestion in mMTC networks while considering SCMA and short-packet communications (SPC). In this paper, we propose an SCMA-based random access (RA) method, in which Q-learning is utilized to dynamically allocate the SCMA codebooks and time-slot groups to MTC devices with the aim of minimizing the RACH congestion in SPC-based mMTC networks. To clarify the benefits of our proposed method, we compare its performance with those of the conventional RA methods with/without Q-learning in terms of RA efficiency and evaluate its convergence. Our simulation results show that the proposed method outperforms the existing methods in overloaded systems, i.e., the number of devices is higher than the number of available RA slots. Moreover, we illustrate the sum rate comparison between SPC and long-packet communications (LPC) when applying the proposed method to achieve more insights on SPC.
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
ERC and FNR
ERC-funded project AGNOSTIC
Researchers ; Professionals ; Students ; General public ; Others
http://hdl.handle.net/10993/47796
H2020 ; 742648 - AGNOSTIC - Actively Enhanced Cognition based Framework for Design of Complex Systems
FnR ; FNR13713801 > Bjorn Ottersten > 5G-Sky > Interconnecting The Sky In 5g And Beyond - A Joint Communication And Control Approach > 01/06/2020 > 31/05/2023 > 2019

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
FINAL_VERSION.pdfAuthor preprint358.56 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.