Maximizing Service Provider’s Profit in Multi-UAV 5G Network Via Deep Reinforcement Learning and Graph Coloring

Abstract

The current 5G network is expected to have a densely populated architecture comprising radio-enabled Service Provider (SP) and heterogeneous User Equipment (UE). Addressing the real-time service demands of UEs with strict deadlines is a critical challenge. Uncrewed Aerial Vehicle (UAV) assisted service provisioning is emerging as an efficient solution for timely service transfers. Therefore, SPs are interested in offering UAV-assisted service transmission to get profited by deploying UAVs. However, this introduces challenges like optimizing the locations of UAVs and Power Level (PL) along with interference management within limited available radio resources. Hence, we proposed a novel framework for multi-UAV-assisted service provisioning, consisting of Base Station (BS), UAVs, and heterogeneous UEs in 5G network. We formulate the SP’s profit maximization problem, optimizing UAVs’ location, PL, and resource allocation while considering service latency, interference management, and UAVs’ energy constraints collectively as an optimization problem. Furthermore, we propose a semi-centralized sub-optimal solution utilizing Multi-agent Deep Reinforcement Learning (MaDRL) and a Graph Coloring-based approach. Extensive simulation analysis demonstrates the proposed algorithm’s effectiveness, achieving an average of 99.05% profit compared to the optimal value.