NOMA in UAV-aided cellular offloading: A machine learning approach

TL;DR

This paper introduces a machine learning framework for optimizing UAV trajectories and power allocation in NOMA-enabled cellular offloading, significantly improving network throughput and spectrum efficiency.

Contribution

It proposes a novel MDQN algorithm for joint 3D trajectory and power optimization in UAV-assisted NOMA networks, outperforming traditional methods.

Findings

MDQN converges faster than conventional DQN in multi-agent scenarios.

NOMA enhances sum rate by 23% over OMA.

Optimal 3D UAV trajectories yield 142% and 56% gains over circular and 2D trajectories.

Abstract

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.