Abstract
Non-orthogonal multiple access (NOMA) networks play an important role in defense communication scenarios. Deep learning (DL)-based solutions are being considered as viable ways to solve the issues in fifth-generation (5G) and beyond 5G (B5G) wireless networks, since they can provide a more realistic solution in the real-world wireless environment. In this work, we consider the deep Q-Network (DQN) algorithm-based user pairing downlink (D/L) NOMA network. We have applied the convex optimization (CO) technique and optimized the sum rate of all the wireless users. First, the near-far (N-F) pairing and near-near and far-far (N-N and F-F) pairing strategies are investigated for the multiple numbers of users, and a closed-form (CF) expression of the achievable rate is derived. After that, the optimal power allocation (OPA) factors are derived using the CO technique. Through simulations, it has been demonstrated that the DQN algorithms perform much better than the deep reinforcement learning (DRL) and conventional orthogonal frequency-division multiple access (OFDMA) schemes. The sum-rate performance significantly increases with OPA factors. The simulation results are in close agreement with the analytical results.
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 callMore From: The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology
Disclaimer: 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.
