• Corpus ID: 235790646

Intelligent Link Adaptation for Grant-Free Access Cellular Networks: A Distributed Deep Reinforcement Learning Approach

  title={Intelligent Link Adaptation for Grant-Free Access Cellular Networks: A Distributed Deep Reinforcement Learning Approach},
  author={Joao V. C. Evangelista and Zeeshan Sattar and Georges Kaddoum and Bassant Selim and Aydin Sarraf},
With the continuous growth of machine-type devices (MTDs), it is expected that massive machine-type communication (mMTC) will be the dominant form of traffic in future wireless networks. Applications based on this technology, have fundamentally different traffic characteristics from human-to-human (H2H) communication, which involves a relatively small number of devices transmitting large packets consistently. Conversely, in mMTC applications, a very large number of MTDs transmit small packets… 
1 Citations

Figures and Tables from this paper

Reliability and User-Plane Latency Analysis of mmWave Massive MIMO for Grant-Free URLLC Applications
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.


Throughput Optimization in Grant-Free NOMA with Deep Reinforcement Learning
A deep reinforcement learning (DRL)- based distributed algorithm is designed for each user to select its pilot sequence via learning from the past pilot sequence selections, which has a better performance than both acknowledgement-based and random selection GF-NOMA schemes.
Grant-Free Access with Multipacket Reception: Analysis and Reinforcement Learning Optimization
This paper abstracts the grant-free access protocols with S IC with SIC with a $K-Multipacket Reception ($K-MPR) model and proposes a reinforcement learning approach to allocate grant- free resources dynamically in order to maximize the normalized throughput of the protocol.
Modeling, Analysis, and Optimization of Grant-Free NOMA in Massive MTC via Stochastic Geometry
This article model, analyze, and optimize the CS-based GF-MONA mMTC system via stochastic geometry (SG) via numerical methods to meet the low-energy-consumption and low-infrastructure-cost demands of IoT applications and shows that CS-free nonorthogonal multiple access with NOP yields better MUD and data rate performances than contention-basedGF-NOMA with orthogonal preambles and grant-free orthogona multiple access.
Joint Physical-Layer and System-Level Power Management for Delay-Sensitive Wireless Communications
This paper formulate the stochastic optimization problem as a Markov decision process (MDP) and solve it online using reinforcement learning (RL), and shows that the proposed learning algorithms can converge up to two orders of magnitude faster than a state-of-the-art learning algorithm for physical layer power-control and up to three orders of orders faster than conventional reinforcement learning algorithms.
Reinforcement Learning for Energy-Efficient Delay-Sensitive CSMA/CA Scheduling
This work designs a reinforcement learning algorithm to solve the single-user problems online so that users can achieve energy-efficient operation while meeting their delay constraints, even though the channel, traffic, and multi-user dynamics are unknown a priori.
Sparse Signal Processing for Grant-Free Massive Connectivity: A Future Paradigm for Random Access Protocols in the Internet of Things
It is argued that massive multiple-input, multiple-output (MIMO) is especially well suited for massive IoT connectivity because the device detection error can be driven to zero asymptotically in the limit as the number of antennas at the base station (BS) goes to infinity by using the multiplemeasurement vector (MMV) compressed sensing techniques.
Cooperative LBT Design and Effective Capacity Analysis for 5G NR Ultra Dense Networks in Unlicensed Spectrum
A new LBT protocol, referred to as cooperative LBT, is designed, in which zero forcing (ZF) precoding is applied to suppress the multi-user interference and the effective capacity of NR-U in unlicensed bands is characterized.
Power control optimization for uplink grant-free URLLC
With full path loss compensation and boosting retransmissions, it is shown that a URLLC load such as 1200 small packets per second per cell can be achieved in the considered scenario and the practical implication of applying power boosting is discussed.
Uplink contention based SCMA for 5G radio access
The uplink contention-based SCMA scheme can be a promising technology for 5G wireless networks for data transmission with low signaling overhead, low delay, and support of massive connectivity.
Analysis of Contention-Based SCMA in mMTC Networks
This paper analyzes the performance of contention-based sparse code multiple access (SCMA) concerning the probability of success of transmission and the area spectral efficiency, and derives closed-form expressions for both performance metrics and validate them with numerical simulations.