Abstract
We propose a hybrid decision framework (HDF) based on Mamdani fuzzy inference system (MFIS) and reinforcement learning (RL). We aim to enhance energy efficiency for non-orthogonal multiple access-unmanned aerial (NOMA-UAV) network. Downlink (DL) power, bandwidth allocation and UAV flying profile is managed, in face of time varying quality of service (QoS) requirements. Energy efficiency, sum-rate, spectral efficiency and successful DL attempts are ascertained. Comparative analysis is carried out between proposed HDF, conventional RL on single DQN (SDQN), and fixed power and bandwidth (FPB) allocation regime. Simulations reveal that HDF surpasses SDQN by margin of 23% and FPB by a margin of 96% in energy efficiency (EE). HDF also surpasses counterparts in DL attempts.
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.
