TY - CHAP
T1 - Multiple Configured-Grants Optimization in Grant-Free NOMA for mURLLC Service
AU - Liu, Yan
AU - Deng, Yansha
AU - Elkashlan, Maged
AU - Nallanathan, Arumugam
AU - Karagiannidis, George K.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/8/31
Y1 - 2022/8/31
N2 - Realizing efficient, delay-bounded, and reliable communications for a massive number of user equipments (UEs) in massive Ultra-Reliable and Low-Latency Communications (mURLLC) is extremely challenging as it needs to simultaneously take into account the latency, reliability, and massive access requirements. To support these requirements, the third generation partnership project (3GPP) has introduced grant-free non-orthogonal multiple access (GF-NOMA) with multiple configured-grants (MCGs), where UE can choose any of these grants as soon as the data arrives. In this paper, we develop a novel learning framework for MCG-GF-NOMA systems. We first design the MCG-GF-NOMA model by characterizing each CG. We then formulate the MCG-GF-NOMA resources configuration problem taking into account three constraints. Finally, we propose a Cooperative Multi-Agent based Double Deep Q-Network (CMA-DDQN) algorithm to allocate the channel resources among MCGs to maximize the number of successful transmissions under the latency constraint. Our results show that the MCG-GF-NOMA framework can simultaneously improve the low latency and high reliability performances for mURLLC.
AB - Realizing efficient, delay-bounded, and reliable communications for a massive number of user equipments (UEs) in massive Ultra-Reliable and Low-Latency Communications (mURLLC) is extremely challenging as it needs to simultaneously take into account the latency, reliability, and massive access requirements. To support these requirements, the third generation partnership project (3GPP) has introduced grant-free non-orthogonal multiple access (GF-NOMA) with multiple configured-grants (MCGs), where UE can choose any of these grants as soon as the data arrives. In this paper, we develop a novel learning framework for MCG-GF-NOMA systems. We first design the MCG-GF-NOMA model by characterizing each CG. We then formulate the MCG-GF-NOMA resources configuration problem taking into account three constraints. Finally, we propose a Cooperative Multi-Agent based Double Deep Q-Network (CMA-DDQN) algorithm to allocate the channel resources among MCGs to maximize the number of successful transmissions under the latency constraint. Our results show that the MCG-GF-NOMA framework can simultaneously improve the low latency and high reliability performances for mURLLC.
KW - deep reinforcement learning
KW - massive URLLC
KW - Multiple configured-grants
KW - NOMA
KW - resource configuration
UR - http://www.scopus.com/inward/record.url?scp=85137275486&partnerID=8YFLogxK
U2 - 10.1109/ICC45855.2022.9838541
DO - 10.1109/ICC45855.2022.9838541
M3 - Conference paper
AN - SCOPUS:85137275486
T3 - IEEE International Conference on Communications
SP - 4516
EP - 4521
BT - ICC 2022 - IEEE International Conference on Communications
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Communications, ICC 2022
Y2 - 16 May 2022 through 20 May 2022
ER -