NOMA in UAV-aided cellular offloading: A machine learning approach
This work addresses cellular network congestion for users by improving offloading efficiency with UAVs, though it is incremental as it builds on existing NOMA and DQN methods.
The paper tackles the problem of optimizing throughput in UAV-aided cellular offloading by jointly designing 3D trajectories and power allocation using a novel mutual deep Q-network (MDQN) algorithm, achieving a 23% higher sum rate with NOMA compared to OMA and up to 142% gains over baseline trajectories.
A novel framework is proposed for cellular offloading with the aid of multiple unmanned aerial vehicles (UAVs), while non-orthogonal multiple access (NOMA) technique is employed at each UAV to further improve the spectrum efficiency of the wireless network. The optimization problem of joint three-dimensional (3D) trajectory design and power allocation is formulated for maximizing the throughput. In an effort to solve this pertinent dynamic problem, a K-means based clustering algorithm is first adopted for periodically partitioning users. Afterward, a mutual deep Q-network (MDQN) algorithm is proposed to jointly determine the optimal 3D trajectory and power allocation of UAVs. In contrast to the conventional deep Q-network (DQN) algorithm, the MDQN algorithm enables the experience of multi-agent to be input into a shared neural network to shorten the training time with the assistance of state abstraction. Numerical results demonstrate that: 1) the proposed MDQN algorithm has a faster convergence rate than the conventional DQN algorithm in the multi-agent case; 2) The achievable sum rate of the NOMA enhanced UAV network is $23\%$ superior to the case of orthogonal multiple access (OMA); 3) By designing the optimal 3D trajectory of UAVs with the aid of the MDON algorithm, the sum rate of the network enjoys ${142\%}$ and ${56\%}$ gains than that of invoking the circular trajectory and the 2D trajectory, respectively.