• Corpus ID: 230433734

A General Deep Reinforcement Learning Framework for Grant-Free NOMA Optimization in mURLLC

@article{Liu2021AGD,
  title={A General Deep Reinforcement Learning Framework for Grant-Free NOMA Optimization in mURLLC},
  author={Yan Liu and Yansha Deng and Hui Zhou and Maged Elkashlan and Arumugam Nallanathan},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.00515}
}
Grant-free non-orthogonal multiple access (GF-NOMA) is a potential technique to support massive Ultra-Reliable and Low-Latency Communication (mURLLC) service. However, the dynamic resource configuration in GF-NOMA systems is challenging due to the random traffics and collisions, which are unknown at the base station (BS). Meanwhile, joint consideration of the latency and reliability requirements makes the resource configuration of GF-NOMA for mURLLC more complex. To address this problem, we… 
Optimization Algorithm for Multipath Transmission of Distance Education Resources Using Reinforcement Learning
TLDR
This study provides a reinforcement learning-based optimization technique for multipath transmission of distance education materials to calculate the optimal transmission rate thresholds in different detection time periods and realize the optimization of resource data transmission efficiency.
Analyzing Uplink Grant-Free Sparse Code Multiple Access System in Massive IoT Networks
TLDR
Simulation results show that denser codebooks can help to support more user equipments (UEs) and increase the reliability of data transmission in a GF- SCMA network, and a higher success probability can be achieved by GF-SCMA with denser UE deployment at low detection thresholds since SCMA can achieve overloading gain.
Reliability and User-Plane Latency Analysis of mmWave Massive MIMO for Grant-Free URLLC Applications
TLDR
This work forms a spatiotemporal mathematical model to evaluate the user-plane latency and reliability performance of millimetre wave (mmWave) massive multipleinput multiple-output (MIMO) URLLC with reactive and Krepetition hybrid automatic repeat request (HARQ) protocols and concludes that mmWave massive MIMO alone is not enough to provide the performance guarantees required by the most stringent URllC applications.

References

SHOWING 1-10 OF 42 REFERENCES
DeepNOMA: A Unified Framework for NOMA Using Deep Multi-Task Learning
TLDR
Deep multi-task learning is resorted for end-to-end optimization of NOMA, by regarding the overlapped transmissions as multiple distinctive but correlated learning tasks, which makes DeepNOMA a universal transceiver optimization approach.
A Novel Analytical Framework for Massive Grant-Free NOMA
TLDR
A novel framework is proposed, where collisions are treated as interference to the remaining received signals and simplified expressions are derived that can well approximate the outage probability and throughput of the system for both successive joint decoding (SJD) and successive interference cancellation (SIC).
Deep Neural Network-Based Active User Detection for Grant-Free NOMA Systems
TLDR
By feeding the training data in the properly designed DNN, the proposed AUD scheme learns the nonlinear mapping between the received NOMA signal and indices of active devices and can handle the whole AUD process, achieving an accurate detection of the active users.
Uplink Nonorthogonal Multiple Access Technologies Toward 5G: A Survey
TLDR
This paper analyzes the state-of-the-art NOMA schemes by comparing the operations applied at the transmitter, as well as the typical grant-free NomA schemes and the detection techniques, and envision the future research challenges deduced from the recently proposed N OMA technologies.
Joint User Activity and Data Detection Based on Structured Compressive Sensing for NOMA
TLDR
A structured iterative support detection algorithm is proposed by exploiting the inherent structured sparsity of user activity naturally existing in NOMA systems to jointly detect user activity and transmitted data in several continuous time slots and can achieve better performance than conventional solutions.
Statistical Delay and Error-Rate Bounded QoS Provisioning for mURLLC Over 6G CF M-MIMO Mobile Networks in the Finite Blocklength Regime
TLDR
Simulation results validate and evaluate the proposed schemes for statistical delay and error-rate bounded QoS provisioning, and formulate and solve the delay violation probability minimization problem and obtain the closed-form solution of the optimal rate adaptation policy for each mobile user over 6G CF m-MIMO mobile wireless networks in the finite blocklength regime.
Deep Learning Aided Grant-Free NOMA Toward Reliable Low-Latency Access in Tactile Internet of Things
TLDR
A variational optimization problem to improve the reliability of grant-free NOMA is formulated by parameterizing the intractable variational function with a specially designed deep neural network, which incorporates random user activation and symbol spreading.
PoC of SCMA-Based Uplink Grant-Free Transmission in UCNC for 5G
TLDR
The focus is on proof of concept of UL grant-free transmissions in the UCNC architecture, which can reduce signaling overhead and transmission latency and is efficiently supported with the SCMA scheme that yields around 230% gain over OFDMA in terms of supported active users.
Comprehensive grant-free random access for massive & low latency communication
  • A. T. Abebe, C. Kang
  • Computer Science
    2017 IEEE International Conference on Communications (ICC)
  • 2017
TLDR
A comprehensive grant-free random access scheme for machine-type communication which is characterized by massive connectivity and low latency, designed in such a way that channel estimation and multi-user detection have a bi-directional mutual relationship.
Analyzing Grant-Free Access for URLLC Service
TLDR
This article proposes a tractable approach to derive and analyze the latent access failure probability of the typical UE under three GF HARQ schemes and presents a spatio-temporal analytical framework for the contention-based GF access analysis.
...
...