Joint Resource, Deployment, and Caching Optimization for AR Applications in Dynamic UAV NOMA Networks

Abstract

The cache-enabling unmanned aerial vehicle (UAV) non-orthogonal multiple access (NOMA) networks for mixture of augmented reality (AR) and normal multimedia applications are investigated, which is assisted by UAV base stations. The user association, power allocation of NOMA, deployment of UAVs and caching placement of UAVs are jointly optimized to minimize the content delivery delay. A branch and bound (BaB) based algorithm is proposed to obtain the per-slot optimization. To cope with the dynamic content requests and mobility of users in practical scenarios, the original optimization problem is transformed to a Stackelberg game. Specifically, the game is decomposed into a leader level user association sub-problem and a number of power allocation, UAV deployment and caching placement follower level sub-problems. The long-term minimization was further solved by a deep reinforcement learning (DRL) based algorithm. Simulation result shows that the content delivery delay of the proposed BaB based algorithm is much lower than benchmark algorithms, as the optimal solution in each time slot is achieved. Meanwhile, the proposed DRL based algorithm achieves a relatively low long-term content delivery delay in the dynamic environment with lower computation complexity than BaB based algorithm.

Resource-Efficient QoS-Aware Video Streaming Using UAV-Assisted Networks

“…The deployment of UANs has been proposed for edge caching and last mile content delivery using UAVs thereby reducing backhaul traffic and improving QoS [12], [27], [28]. Even a modest cache size of 100 Mbits can reduce the backhaul traffic by more than 50% in favorable cases [29,Fig.…”

AI-Enabled UAV Communications: Challenges and Future Directions

“…It solved the UAV path planning with unknown channel states but with specific area. In [81], the authors studied the topic of providing the optimum quality of service (QoS) in UAV-assisted cellular networks. To effectively optimize the usefulness of the UAV, it has suggested a combination design of access point selection and UAV path planning.…”

“…[91] UAV+D2D [77] UAV Trajectory [99] UAV+wireless network [92] UAV+IoT [93] Trajectory MIMO-UAV [78] UAV+Trajectory [79] UAV Design [80] RIS Trajectory [102] UAV Trajectory [100] UAV TrajectoryIoV [105] UAV Trajectory [106] Design UAV [81] UAV+aNOMA [82] UAVIOT+Allocat resources [83] Mobile edge computing [84] UAV Trajectory [85] Mobile edge computing [125] UAV+NOMA [114] UAV Beam selection [73] Improve UAV throughput [110] Modeling UAV trajectory [89] Mobile edge computing [126] UAV placement & resource allocation [90] Multi-access edge computing [87] Cloud assisted joint charging SchedulingEnergy management [86] UAV Trajectory Federated Learning [119] UAV+IoT [103] Survey [120] UAV+Image Classification [126] UAV placement & resource allocation…”

Multi-Agent DRL for Resource Allocation and Cache Design in Terrestrial-Satellite Networks

“…In [32], the authors decomposed the joint base station and user cache optimization problem into two subproblems, then they applied value function approximation Q-learning and DQN to solve these two subproblems. In [33], the authors proposed a DRL-based algorithm, which can optimize the user association, power allocation of NOMA, deployment of unmanned aerial vehicle (UAV) and caching placement of UAVs to jointly to minimize the content delivery delay. The [34] proposed a Q-learning based caching placement and resource allocation algorithm.…”