Wireless Communications and Mobile Computing

Artificial Intelligence for Cognitive Radio Networks


Publishing date
01 Sep 2021
Status
Closed
Submission deadline
14 May 2021

Lead Editor

1SRM Institute of Science and Technology, Chennai, India

2Sri Chandrasekharendra Saraswathi Viswamahavidyalaya, Kancheepuram, India

3Deakin University, Geelong, Australia

This issue is now closed for submissions.
More articles will be published in the near future.

Artificial Intelligence for Cognitive Radio Networks

This issue is now closed for submissions.
More articles will be published in the near future.

Description

In this digital era, billions of smart devices are connected together globally. The massive increase in the number of wireless smart devices requires increased spectrum resources. But with limited spectrum resources, there is a need to find an alternative where the spectrum resources are efficiently managed and utilized. Cognitive radio (CR) defines the dynamic behavioural model of the radio network for improved spectrum and bandwidth usage. CR identifies the free channels in the spectrum and uses it for communication by dynamically changing the transmission parameters and leads to the better utilization of channel resources. CR defines two types of users: primary users (PU) and secondary users (SU) in the network. CR assigns the unused PU channels to SU and again when the channel is needed for PU, the channels will be reassigned to PU. In the current context, cognitive radios are expected to possess learning and decision-making capabilities. Some of the applications of cognitive radios are selecting low-cost radio channels, improved spectrum utilization, establishing reliable links, etc. In addition, channel quality is an important factor for reliable communication which must be ensured by CR. Thus, CR has to ensure efficient channel utilization and accessing better quality channels for SU data transmission. Additionally, when the allotted channels for SU is again given back to PU, CR should assign new channels for SU. On assigning and reassigning the channels between PU and SU, there should be no security flaws in the network. In the aforementioned applications, CR is expected to be fully aware of its network parameters and should have the capability of dynamically changing its network behaviour to make use of the available bandwidth and quality channels.

Artificial Intelligence (AI) is the set of techniques that mimics human ways of thinking and capabilities in machines. The dynamicity and decision making required by the CR will be supported by AI techniques. In general, CR exhibits sensing, learning, reasoning, and adapting to the spectrum environment. In the learning and reasoning phase of CR, AI techniques are having profound applications. A robust AI technique for learning and reasoning of CR will increase its efficiency and security by multiple factors. Machine learning (ML) and Reinforcement Learning (RL) algorithms are also giving promise to an energy-efficient model for cognitive networks. AI-based CR will improve the efficiency and widespread usability of Wireless Sensor Networks (WSN), Industrial Internet of Things (IIoT), Software Defined Networks (SDN), and Mobile Ad hoc Networks (MANET).

The aim of this Special Issue is to explore the recent advancements made in CR networks with the support of AI techniques. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

  • Novel AI-enabled radio and network framework, algorithms, convergence, and performance analysis
  • Cognitive radio for wireless sensor network deployment
  • AI for physical layer issues, e.g., channel estimation, interference alignment, and coding
  • AI-inspired MAC and routing protocols for CR network
  • AI algorithms in network access and transmit control, e.g., channel allocation, power and rate control
  • AI-based dynamic channel switching in CR
  • Practical applications of CR in wireless sensor networks testbed
  • AI algorithms for traffic engineering, scheduling, network slicing, and virtualization
  • AI algorithms in mobile edge computing, wireless caching, and mobile data offloading
  • AI algorithms for network economics, auctions, multi-agent learning, and crowdsourcing
  • Signal estimation and traffic parameter estimation using AI in CR
  • Security measures in the cognitive wireless networks
  • Dynamic network infrastructure management analysis through AI
  • Collaborative IoT network sensor management using AI
  • Machine learning and reinforcement learning for improving energy efficiency models of cognitive wireless networks
Wireless Communications and Mobile Computing
Publishing Collaboration
More info
Wiley Hindawi logo
 Journal metrics
Acceptance rate33%
Submission to final decision81 days
Acceptance to publication37 days
CiteScore4.300
Journal Citation Indicator0.390
Impact Factor2.336
 Submit

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.