Joint Control of Random Access and Dynamic Uplink Resource Dimensioning for Massive MTC in 5G NR Based on SCMA

Miuccio, Luciano; Panno, Daniela; Riolo, Salvatore

doi:10.1109/jiot.2020.2974402

Cited by 37 publications

(26 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from others, in [19] using 2D matching theory authors performed dynamic resource allocations considering energy efficiency for downlink NOMA. Similarly, in [12] for the massive Machine Type Communications (mMTC) usage scenario, also known as massive Internet of Things (mIoT) dynamic resource management is performed with Sparse Code Multiple Access (SCMA) domain using conventional mathematical tools. The authors in [20] proposed a general power allocation scheme for uplink and downlink NOMA to guarantee the quality of service (QoS).…”

Section: A Related Work and Motivations 1) Studies On Noma-iot Netwmentioning

confidence: 99%

“…The second strategy a i is a result of selected switching strategy a s , a i denotes an index of the 3D associations among users, BSs, and sub-channels. Finally, the DRL agent uses loss function mentioned in (12) to calculate θ based on the previous experience.…”

Section: ) a Is A Multi-dimensional Matrix Representing Actionsmentioning

confidence: 99%

“…In this way, initial weights are also calculated to start the optimization process. • Line #(4 − 17): Whole process for DRL is similar to SARSA from line #(5−11) with DRL bellmen equations (12) to (19). • Loss Calculation: The equation 12is to calculate the loss θ that is the mean squared error (MSE) indicating the difference of the target and predicted networks.…”

Section: Definition 4 Drl Design In This Work Is Defined With Two Mamentioning

confidence: 99%

“…On the other hand, θ ′ weights are based on the previous episodes and these weights are fixed during the calculation of θ for training purpose. Additionally, We utilize MSE loss function (12) to evaluate the accuracy of the training for the target network. Therefore, the proposed loss function is based on θ and θ ′ to check the deviation of the predicted DNN weights.…”

Section: Definition 4 Drl Design In This Work Is Defined With Two Mamentioning

confidence: 99%

“…Especially in practical NOMA systems by allowing resource share among more than one users the process is more dynamic when users are simultaneously joining and leaving the network in short term and long term basis. Numerous model-based techniques target to solve dynamic behaviour of wireless networks but failed to provide long-term performance outcomes [9], [10], [11], [12] and [13]. Moreover, due to the absence of learning abilities, to provide long term network stability the computational complexity of traditional schemes becomes ultra-high.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach

Ahsan

Qin

et al. 2021

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) exploits the potential of the power domain to enhance the connectivity for the Internet of Things (IoT). Due to time-varying communication channels, dynamic user clustering is a promising method to increase the throughput of NOMA-IoT networks. This paper develops an intelligent resource allocation scheme for uplink NOMA-IoT communications. To maximise the average performance of sum rates, this work designs an efficient optimization approach based on two reinforcement learning algorithms, namely deep reinforcement learning (DRL) and SARSA-learning. For light traffic, SARSA-learning is used to explore the safest resource allocation policy with low cost. For heavy traffic, DRL is used to handle traffic-introduced huge variables. With the aid of the considered approach, this work addresses two main problems of fair resource allocation in NOMA techniques: 1) allocating users dynamically and 2) balancing resource blocks and network traffic. We analytically demonstrate that the rate of convergence is inversely proportional to network sizes. Numerical results show that: 1) Compared with the optimal benchmark scheme, the proposed DRL and SARSA-learning algorithms have lower complexity with acceptable accuracy and 2) NOMA-enabled IoT networks outperform the conventional orthogonal multiple access based IoT networks in terms of system throughput.

show abstract

Section: A Related Work and Motivations 1) Studies On Noma-iot Netwmentioning

confidence: 99%

Section: ) a Is A Multi-dimensional Matrix Representing Actionsmentioning

confidence: 99%

Section: Definition 4 Drl Design In This Work Is Defined With Two Mamentioning

confidence: 99%

Section: Definition 4 Drl Design In This Work Is Defined With Two Mamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach

Ahsan

Qin

et al. 2021

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

An intelligent resource allocation strategy for machine type communication environment

Sharmila,

Satyanarayana

2023

Int J Communication

View full text Add to dashboard Cite

SummaryMobile communication has multiplied in many digital intelligent applications. The machine‐type communication (MTC) services have afforded flexible communication facilities considering those facilities. However, high energy consumption and poor data rate have made the MTC a complex system. So, the resource allocation strategy has been introduced by different procedures such as neural models, optimization, and mathematical models. But, in some cases, these algorithms have recorded high complexity and high resource requirement. Hence, the present research article has planned to develop a novel Chimp‐based Extreme Neural Model (CbENM) for allocating the desired optimal resource for each machine user. Moreover, the resources were assigned based on the task completion deadline. Before the resource allocation process, the active state users were predicted by analyzing their data rate and deadlines. Finally, the desired resources were allocated to each user, and the performance was validated. The presented model has a lower delay bond rate and a high data aggregate rate.

show abstract

Research on Random Access Control Strategy and Optimization Algorithm of Multi-type Terminals Based on Deep Reinforcement Learning

Yuan,

Yan,

Ouyang

et al. 2024

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Joint Control of Random Access and Dynamic Uplink Resource Dimensioning for Massive MTC in 5G NR Based on SCMA

Cited by 37 publications

References 36 publications

Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach

Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach

An intelligent resource allocation strategy for machine type communication environment

Research on Random Access Control Strategy and Optimization Algorithm of Multi-type Terminals Based on Deep Reinforcement Learning

Contact Info

Product

Resources

About