Abstract
This paper studies the initial contention window (CW) size adjustment problem in an NR-U and WiFi coexistence network with an NR-U system and a WiFi system. The problem is formulated as an initial CW size optimization problem with an objective to adaptively find an optimal initial CW size such that the throughput of the NR-U system is maximized while the throughput of the WiFi system is guaranteed. To solve the problem, a Deep Recurrent Q-Network (DRQN) based initial CW size optimization algorithm is proposed to adaptively find an optimal CW size by training the main DQN in a DRQN and observing the current status of the coexistence network, including the current CW size, the throughput of the WiFi system, the throughput of the NR-U system, and the number of NR-U users that have data to transmit. Simulation results show that the proposed DRQN-based CW optimization algorithm outperforms a fixed CW mechanism and an adaptive CW mechanism in terms of the throughput of the NR-U system and the fairness of the coexistence network.
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.
