Abstract
AbstractCooperative communication systems use cooperative relays for transmitting their data packets to the destination. Cooperative communication schemes having all relays participating in transmission may cause unnecessary wastes of most valuable spectrum resources. So it is mandatory to effectively select a transmission mode for cooperative cognitive radio networks (CCRNs). In this paper, an efficient transmission mode scheme based on Q-learning algorithm is proposed. State, action, and reward are defined to achieve a good performance on time delay and energy efficiency in data transmission as well as the interference to primary users during secondary users transmission. The proposed scheme selects an optimal action on the networks environment to maximize the total revenue of the multilateral metric. The simulation result shows that the proposed scheme can efficiently support the determination for the transmission mode and outperforms conventional schemes for a single metric in CCRNs.
Highlights
Cognitive radio is a promising wireless technology to resolve the growing scarcity of the indispensable electromagnetic spectrum resources
An efficient transmission mode scheme based on the reinforcement learning for cooperative cognitive radio networks (CCRNs) is proposed to allow the secondary users (SUs) source to effectively determine an optimal action for maximizing a given multilateral metric and to provide operations with low complexity through Q-learning that is a type of the reinforcement learning
May require a complicated system approach because quality of services (QoS) requirements make up a multilateral metric and there exist contradictory system objectives
Summary
Cognitive radio is a promising wireless technology to resolve the growing scarcity of the indispensable electromagnetic spectrum resources. The context of the transmission mode in CCNs becomes more complex in CCRNs due to the SA of the PUs. In this paper, an efficient transmission mode scheme based on the reinforcement learning for CCRNs is proposed to allow the SU source to effectively determine an optimal action for maximizing a given multilateral metric and to provide operations with low complexity through Q-learning that is a type of the reinforcement learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
