Filters








266 Hits in 4.3 sec

Throughput and Latency in the Distributed Q-Learning Random Access mMTC Networks [article]

Giovanni Maciel Ferreira Silva, Taufik Abrao
2021 arXiv   pre-print
In mMTC mode, with thousands of devices trying to access network resources sporadically, the problem of random access (RA) and collisions between devices that select the same resources becomes crucial.  ...  Our numerical results indicated that the proposed distributed packet-based Q-learning method attains a much better throughput-latency trade-off than the alternative independent and collaborative techniques  ...  Conclusions Q-Learning-based random access methods for mMTC networks have been investigated in terms of throughput and latency.  ... 
arXiv:2111.00299v1 fatcat:qnp3qw476reaxee7javkszzeha

BLER-based Adaptive Q-learning for Efficient Random Access in NOMA-based mMTC Networks

Duc-Dung Tran, Shree Krishna Sharma, Symeon Chatzinotas
2021 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring)  
In this paper, we propose an adaptive Q-learning (AQL) algorithm based on block error rate (BLER), an important metric in SPC, for a non-orthogonal multiple access (NOMA) based mMTC system.  ...  The performance of the proposed AQL method is compared with the recent Q-learning solutions in the literature in terms of system throughput over a range of parameters such as the number of devices, blocklength  ...  To further improve the ability of RAN congestion avoidance in mMTC networks, the use of Q-learning and non-orthogonal multiple access (NOMA) was considered in [11] .  ... 
doi:10.1109/vtc2021-spring51267.2021.9448787 fatcat:eowb3th67ffbbjai4vchobi7fa

LSTM-Aided Hybrid Random Access Scheme for 6G Machine Type Communication Networks [article]

Huimei Han, Wenchao Zhai, Fuhui Zhou, Lei Liu, Jinsong Wu, Ning Zhang, Jun Zhao
2021 arXiv   pre-print
is completed in two steps coupled with the mMTC devices' access procedure to reduce latency.  ...  In the proposed LSTMH-RA scheme, mMTC devices access the network via a timing advance (TA)-aided four-step procedure to meet massive access requirement, while the access procedure of the URLLC devices  ...  Otherwise, this device fails to access the network and will access the network in the upcoming random access time slot.  ... 
arXiv:2012.13537v6 fatcat:leetnioxnnhcpjk3qknmte3teq

Towards Massive Machine Type Communications in Ultra-Dense Cellular IoT Networks: Current Issues and Machine Learning-Assisted Solutions

Shree Krishna Sharma, Xianbin Wang
2019 IEEE Communications Surveys and Tutorials  
Along with the highlights on the inefficiency of the legacy Random Access (RA) procedure in the mMTC scenario, we then present the key features and channel access mechanisms in the emerging cellular IoT  ...  Out of several ML techniques, we focus on the application of low-complexity Q-learning approach in the mMTC scenario along with the recent advances towards enhancing its learning performance and convergence  ...  challenges for enhancing the access latency, scalability, connection reliability, energy efficiency and network throughput.  ... 
doi:10.1109/comst.2019.2916177 fatcat:vj7pau7mi5ch5ne6akgvrrtsla

Q-Learning-Based SCMA for Efficient Random Access in mMTC Networks With Short Packets

Duc-Dung Tran, Shree Krishna Sharma, Symeon Chatzinotas, Isaac Woungang
2021 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)  
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  ...  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.  ...  ACKNOWLEDGMENT This work was supported in part by the FNR-funded project CORE 5G-Sky under Grant C19/IS/13713801, and ERC-funded project Agnostic under Grant 742648.  ... 
doi:10.1109/pimrc50174.2021.9569713 fatcat:li5yjcprhzghfkdx4dcjdz7jie

Towards Massive Machine Type Communications in Ultra-Dense Cellular IoT Networks: Current Issues and Machine Learning-Assisted Solutions [article]

Shree Krishna Sharma, Xianbin Wang
2018 arXiv   pre-print
Along with the highlights on the inefficiency of the legacy Random Access (RA) procedure in the mMTC scenario, we then present the key features and channel access mechanisms in the emerging cellular IoT  ...  Out of several ML techniques, we focus on the application of low-complexity Q-learning approach in the mMTC scenarios.  ...  challenges for enhancing the access latency, scalability, connection reliability, energy efficiency and network throughput.  ... 
arXiv:1808.02924v1 fatcat:iplhjubgbrafrdz4temdnfnjqa

RAN Resource Slicing in 5G Using Multi-Agent Correlated Q-Learning [article]

Hao Zhou, Medhat Elsayed, Melike Erol-Kantarci
2021 arXiv   pre-print
The proposed correlated Q-learning based interslice RB allocation (COQRA) scheme is compared with Nash Q-learning (NQL), Latency-Reliability-Throughput Q-learning (LRTQ) methods, and the priority proportional  ...  Our simulation results show that the proposed COQRA achieves 32.4% lower latency and 6.3% higher throughput when compared with LRTQ, and 5.8% lower latency and 5.9% higher throughput than NQL.  ...  Shahram Mollahasani for his generous help and useful discussions. This work is funded by the NSERC CREATE and Canada Research Chairs programs.  ... 
arXiv:2107.01018v1 fatcat:ikljqecqtzem3f5ix7sj3jmuiy

Towards Massive Connectivity Support for Scalable mMTC Communications in 5G networks [article]

Carsten Bockelmann, Nuno K. Pratas, Gerhard Wunder, Stephan Saur, Monica Navarro, David Gregoratti, Guillaume Vivier, Elisabeth de Carvalho, Yalei Ji, Cedomir Stefanovic, Petar Popovski, Qi Wang, Malte Schellmann, Evangelos Kosmatos, Panagiotis Demestichas (+3 others)
2018 arXiv   pre-print
Specifically, we present an overview of different physical and medium access techniques to address the problem of a massive number of access attempts in mMTC and discuss the protocol performance of these  ...  In this paper we focus on the massive Machine Type Communications (mMTC) service within a multi-service air interface.  ...  and the latency of the last successful random access.  ... 
arXiv:1804.01701v1 fatcat:rxmtp2lrjncstjiabqkntm7niu

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

Joao V.C. Evangelista, Zeeshan Sattar, Georges Kaddoum, Bassant Selim, Aydin Sarraf
2021 arXiv   pre-print
The problem of physical layer (PHY) and medium access control (MAC) optimization in grant-free random access transmission is is modeled as a partially observable stochastic game (POSG) aimed at minimizing  ...  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.  ...  SYSTEM MODEL In this paper, we consider the problem of designing a distributed link adaptation solution for a grant-free access 5G network providing mMTC service.  ... 
arXiv:2107.04145v1 fatcat:hov6f5v2q5bfphyim4ali4o2te

Six Key Enablers for Machine Type Communication in 6G [article]

Nurul Huda Mahmood, Hirley Alves, Onel Alcaraz López, Mohammad Shehab, Diana P. Moya Osorio, Matti Latva-aho
2019 arXiv   pre-print
Driven by impetus to provide vertical-specific wireless network solutions, machine type communication encompassing both its mission critical and massive connectivity aspects is foreseen to be an important  ...  While 5G is being rolled out in different parts of the globe, few research groups around the world - such as the Finnish 6G Flagship program - have already started posing the question: What will 6G be?  ...  as Markov decision processes and Q-learning in competitive scenarios.  ... 
arXiv:1903.05406v1 fatcat:wsrguijsfjbe7p5lf6a3ibr5lm

URLLC for 5G and Beyond: Requirements, Enabling Incumbent Technologies and Network Intelligence

Rashid Ali, Yousaf Bin Zikria, Ali Kashif Bashir, Sahil Garg, Hyung Seok Kim
2021 IEEE Access  
RANDOM ACCESS CHANNEL MECHANISM One of the most basic sources of latency in 5G systems is the underlying link association with the assistance of an random access channel (RACH) method that causes several  ...  [161] used federated learning (FL) in a distributed learning environment for task scheduling in wireless networks, named as multi-task learning (MTL).  ...  He taught numerous courses in the field of computer science and engineering, from reinforcement learning to computer networks.  ... 
doi:10.1109/access.2021.3073806 fatcat:7ngx3ah5vzdyvcz4nkd2vvdyjy

Reinforcement Learning-based Resource Management Model for Fog Radio Access Network Architectures in 5G

Nosipho N. Khumalo, Olutayo O. Oyerinde, Luzango Mfupe
2021 IEEE Access  
paradigm in fifth generation (5G) mobile networks in the form of fog radio access network (F-RAN).  ...  Reinforcement learning (RL) is presented as a method for dynamic and autonomous resource allocation, and an algorithm is proposed based on Q-learning.  ...  The work in [18] attempted to achieve ultra-low latency by presenting a distributed content sharing and computing mechanism combined with the greedy algorithm.  ... 
doi:10.1109/access.2021.3051695 fatcat:ijiatyzhgnad3jhrmc4qzebrbi

Reinforcement Learning for Dynamic Resource Optimization in 5G Radio Access Network Slicing [article]

Yi Shi, Yalin E. Sagduyu, Tugba Erpek
2020 arXiv   pre-print
Results show that reinforcement learning provides major improvements in the 5G network utility relative to myopic, random, and first come first served solutions.  ...  Therefore, a Q-learning solution is presented to maximize the network utility in terms of the total weight of granted network slicing requests over a time horizon subject to communication and computational  ...  on the throughput and latency requirements.  ... 
arXiv:2009.06579v1 fatcat:5647a4mhdzdrjitigghqklf7ie

Proactive Traffic Offloading in Dynamic Integrated Multi-Satellite Terrestrial Networks [article]

Wiem Abderrahim, Osama Amin, Mohamed-Slim Alouini, Basem Shihada
2022 arXiv   pre-print
Our findings prove the importance of the cooperation between the multi-satellite network and the terrestrial network conditioned by traffic prediction to enhance the performance of IMTSN in terms of latency  ...  The integration between the satellite network and the terrestrial network will play a key role in the upcoming sixth-generation (6G) of mobile cellular networks thanks to the wide coverage and bandwidth  ...  traffic requirements in terms of reliability, latency and throughput.  ... 
arXiv:2205.04940v1 fatcat:jnx6dotjubbqrozncmzjxaqpiu

Competitive MA-DRL for Transmit Power Pool Design in Semi-Grant-Free NOMA Systems [article]

Muhammad Fayaz, Wenqiang Yi, Yuanwei Liu, Arumugam Nallanathan
2021 arXiv   pre-print
gain in terms of the system throughput, respectively.  ...  In this paper, we exploit the capability of multi-agent deep reinforcement learning (MA-DRL) technique to generate a transmit power pool (PP) for Internet of things (IoT) networks with semi-grant-free  ...  To enable the accomplishment of mMTC, as well as ensuring the quality of service (QoS) with low latency communication and small signalling overhead, NOMA with two types of access methods, i.e., grant-free  ... 
arXiv:2106.11190v1 fatcat:taarosli3zga7aviedyy5a2yti
« Previous Showing results 1 — 15 out of 266 results