Deep Reinforcement Learning Based Resource Allocation For Narrowband Cognitive Radio-IoT Systems

Muteba, K.F.; Djouani, Karim; Olwal, Thomas O.

doi:10.1016/j.procs.2020.07.046

Cited by 14 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, in these circumstances, whenever, primary users signal-to-noise ratio rises, it turns out handy for secondary users to sense activity of primary users, which eventually improves secondary users throughput. Here, the RL-based MAC outperforms the LMAC (up to 35%) and SMAC (up to 25%) method [3] in terms of aggregated throughput. Another experimental analysis as revealed in Figure 12, shows the impact on network throughput with channel switching frequency.…”

Section: Results Analysismentioning

confidence: 94%

See 1 more Smart Citation

Untitled

2022

IJCNC

View full text Add to dashboard Cite

The coupling of multiple protocol layers for a Cognitive Radio-based Industrial Internet of Ad-hoc Sensor Network, enables better interaction, coordination, and joint optimization of different protocols in achieving remarkable performance improvements. In this paper, network, and medium access control (MAC) layer functionalities are cross-layered by developing the joint strategy of routing and effective spectrum sensing and Dynamic Channel Selection (DCS) using the Reinforcement Learning (RL) algorithm. In an industrial ad-hoc scenario, the network layer utilizes the sensed spectrum and selected channel by MAC layer for next-hop routing. MAC layer utilizes the lowest known transmission delay of a channel for a single hop as computed by the network layer, which improves the MAC channel selection operation. The applied RLbased technique (Q learning) enables the CR Secondary Users (SUs) to sense, learn, and make the optimal decision on their environment of operations. The proposed RLCLD schemes improve the SU network performance up to 30% as compared to conventional methods.

show abstract

Section: Results Analysismentioning

confidence: 94%

“…This might lead to large overhead and chances of false spectrum detection. Additionally, frequent spectrum sensing, spectrum handover, and link disconnection cause limited energy of the battery-powered sensors and poor network coverage of the quality of service (QoS) hungry sensor nodes [3].…”

Section: Introductionmentioning

confidence: 99%

Untitled

2022

IJCNC

View full text Add to dashboard Cite

show abstract

“…In the third scenario of tests, the algorithm is compared with the recent ML algorithms presented in Ref. [72]: A traditional Q‐learning algorithm. DQN‐based algorithm. …”

Section: Simulation Results and Discussionmentioning

confidence: 99%

“…To overcome such drawbacks, the authors in Ref. [44] propose DRL as an interactive mechanism between Q‐learning and the Markov decision process (MDP), to reduce the number of repeated transmissions and maximise the number of satisfied IoT devices. In Ref.…”

Section: Literature Reviewmentioning

confidence: 99%

“…On the basis of spectrum utilisation, the reward function is expressed as [44]:

r(s,a)=\sum\limits _{n=1}^{N/2}{\mathrm{log}}_{2}\left(1+k{\gamma }_{n}\right)

where:

k=1.5/{\mathrm{ln}}^{\left(0.2/BE{R}_{\mathit{tar}}\right)}

BER tar is the threshold of error bit rate, and γ n is the ratio of signal to interference for the link n in the communication channel.

{\gamma }_{n}=\frac{{P}_{n}{G}_{nn}}{{n}_{0}\sum\limits _{j=1,j\ne n}{P}_{j}{G}_{jn}{\epsilon}(j,n)}

…”

Section: Approach To Cognitive Radio Controlmentioning

confidence: 99%

See 1 more Smart Citation

Distributed reinforcement learning for dynamic spectrum allocation in cognitive radio‐based internet of things

Elhachmi

2022

IET Networks

View full text Add to dashboard Cite

Cognitive Radio (CR) with other advancements such as the Internet of things and machine learning has recently emerged as the main involved technique to use spectrum in an efficient manner. It can access the spectrum in a fully dynamic way and exploit the unused spectrum resources without creating any harm to cognitive users. In this paper, the authors develop a CR access strategy founded on the implementation of an efficient Deep Multi‐user Reinforcement Learning algorithm based on a combination of a Deep neural network, Q‐learning, and cooperative multi‐agent systems. The proposed approach consists of two stages: the user choice algorithm to set up an agent's activation order, and the frequency choice method to select the optimal channel on the appropriate bandwidth. Reasonable implementation is proposed, and the obtained results demonstrate that the authors’ approach can improve wireless communication for all CR terminals. It shows satisfactory performances in terms of user satisfaction degree and the number of used channels and can keep the channel allocation plan always in the appropriate state.

show abstract