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

Elhachmi, Jamal

doi:10.1049/ntw2.12051

Cited by 8 publications

(7 citation statements)

References 74 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HALAKI ET AL. gorithms, in addition to the classical methods of SS, have received considerable research interest in ref [25][26][27][28][29]. ML algorithms utilise a set of experimental observations as a training data set thereby requiring prior information of the incumbent signal.…”

Section: Related Workmentioning

confidence: 99%

“…A detailed study on the application, requirements and challenges are discussed by authors in ref [31]. Application of ML algorithm in CR [25] and an Internet of vehicles enabled by CR is proposed in literature [32]. These applications are targeted towards achieving the goals of 6G communication.…”

Section: Related Workmentioning

confidence: 99%

“…Further, in ML based SS techniques [25][26][27][28][29], training data set is required for successful implementation. However, our proposed detectors do not depend on any prior information of the modulation scheme utilised by the incumbent signal.…”

Section: Motivationmentioning

confidence: 99%

See 2 more Smart Citations

Norm‐based spectrum sensing for cognitive radios under generalised Gaussian noise

et al. 2023

View full text Add to dashboard Cite

Cognitive radio (CR) systems are configured to dynamically assess the spectrum utilisation and contribute towards an improved spectrum efficiency. Hence, accurate detection of the incumbent signal in a given channel, popularly known as spectrum sensing (SS), is essential for CR. Here, in the domain of SS, the authors introduce a new goodness‐of‐fit test (GoFT) founded on p‐norm of the observations at the receiver node. To capture the heavy‐tailed nature of noise distribution in practical communication channels, the authors utilise generalised Gaussian distribution (GGD) as a noise model. A novel p‐norm detector (PND) and a geometric power detector (GPD) is proposed and corresponding probability density function (PDF) under GGD is derived. Via Monte Carlo simulations, the authors show a match of the derived PDFs with the simulation results. Using Neyman‐Pearson framework the performances of PND and GPD are compared with an existing differential entropy detector (DED), the well‐known energy detector (ED) and joint correlation and energy detector (CED) under GGD noise model. Evaluation of proposed PND and GPD utilising Monte Carlo simulations indicate a superior performance. Further, the experiments employing real‐world data establish superiority of the proposed detectors as compared to existing techniques. The authors derive and implement an optimised threshold for PND, providing further improvement in performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Norm‐based spectrum sensing for cognitive radios under generalised Gaussian noise

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In ref. [13], the authors propose a reinforcement learning (RL) based signal detection technique for CR and suggests its application in internet‐of‐things (IoT). RL‐based techniques are further utilised in ref.…”

Section: Introductionmentioning

confidence: 99%

Vasicek and Van Es entropy‐based spectrum sensing for cognitive radios

2023

View full text Add to dashboard Cite

Accurate detection of spectrum holes is a useful requirement for cognitive radios that improves the efficiency of spectrum usage. The authors propose three novel, simple, and entropy‐based detectors for spectrum sensing in cognitive radio. The authors evaluate the probability of detection of these three detectors: Vasicek's entropy detector, truncated Vasicek's entropy detector, and Van Es' entropy detector, over a predefined probability of false‐alarm. In particular, the authors provide the approximate and asymptotic test statistics for these detectors in the presence and absence of Nakagami‐m fading, noise variance uncertainty, and optimised detection threshold. Furthermore, the authors provide a detailed comparison study among all the detectors via Monte Carlo simulations and justify authors results through real‐world data. The authors’ experimental results establish a superior performance of truncated Vasicek's entropy detector over Vasicek's entropy detector, energy detector, differential entropy detector and Van Es' entropy detector in practically viable scenarios.

show abstract

“…Reinforcement learning (RL) [16] is a type of machine learning that takes the actions that optimize the benefits based on the current environment [17][18]. A classic example is the obstacle avoidance system used in robot vacuums [19].…”

Section: Introductionmentioning

confidence: 99%

Automatic Path Planning for Spraying Drones Based on Deep Q-Learning

Huang¹,

Huang²,

Li³

et al. 2023

Journal of Internet Technology

View full text Add to dashboard Cite

<p>The reduction of the agricultural workforce due to the rapid development of technology has resulted in labor shortages. Agricultural mechanization, such as drone use for pesticide spraying, can solve this problem. However, the terrain, culture, and operational limitations in mountainous orchards in Taiwan make pesticide spraying challenging. By combining reinforcement learning with deep neural networks, we propose to train drones to avoid obstacles and find optimal paths for pesticide spraying that reduce operational difficulties, pesticide costs, and battery consumption. We experimented with different reward mechanisms, neural network depths, flight direction granularities, and environments to devise a plan suitable for sloping orchards. Reinforcement learning is more effective than traditional algorithms for solving path planning in complex environments.</p> <p> </p>

show abstract

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

Cited by 8 publications

References 74 publications

Norm‐based spectrum sensing for cognitive radios under generalised Gaussian noise

Norm‐based spectrum sensing for cognitive radios under generalised Gaussian noise

Vasicek and Van Es entropy‐based spectrum sensing for cognitive radios

Automatic Path Planning for Spraying Drones Based on Deep Q-Learning

Contact Info

Product

Resources

About