Resource Management for Transmit Power Minimization in UAV-Assisted RIS HetNets Supported by Dual Connectivity

This paper proposes a novel approach to improve the performance of heterogeneous network (HetNet) supported by dual connectivity (DC) adopting multiple unmanned aerial vehicles (UAVs) as passive relays that carry reconfigurable intelligent surfaces (RISs). More specifically, RISs are deployed under UAVs termed UAVs-RISs operate over micro-wave ( $\mu \text{W}$ ) channel in sky sustain strong line-of-sight (LoS) connection with ground users. The macro-cell operates based on orthogonal access (OMA), while small base stations (SBSs) millimeter-wave (mmW) non-orthogonal (NOMA). We study problem total transmit power minimization jointly optimizing trajectory/velocity each UAV, RISs’ phase shifts, subcarrier allocations, and active beamformers at BS. underlying is highly non-convex global optimal solution intractable. To handle it, we decompose original into two subproblems, i.e., subproblem which deals UAVs’ trajectories/velocities, allocations for ; beamforming design allocation mmW. In particular, solve first via dueling deep Q-Network (DQN) learning developing distributed algorithm leads better policy evaluation. Then, mmW successive convex approximation (SCA) method. Simulation results exhibit effectiveness proposed resource scheme compared other baseline schemes. it revealed deploying UAVs-RISs, can be reduced 6 dBm maintaining similar guaranteed QoS.