Deep-EERA: DRL-based Energy-Efficient Resource Allocation in UAV-Empowered Beyond 5G Networks

The advent of innovative and interactive applications like online gaming, digital twins, smart healthcare, smart cities, Internet of Things (IoT) services, and various industrial sectors has created a demand for high data rates, seamless connection, and ultra-low latency. Meeting these diverse application requirements is very challenging for 5G and Beyond 5G (B5G) networks. So, there is a pressing requirement for a cost-effective solution to enhance the spectral efficiency of B5G networks in densely populated areas, enabling higher data rates and uninterrupted connectivity while minimizing costs. Unmanned Aerial Vehicles (UAVs) serving as Aerial Base Stations (ABSs) in communication networks emerged as an innovative, cost-effective solution for bolstering network capacity. They prove particularly effective in handling emergencies, disasters, device failures, and sudden surges in high-data-rate demands. Nevertheless, integrating UAVs into the B5G networks presents new challenges, including resource scarcity, energy efficiency, resource allocation, optimal power transmission control, and maximizing overall throughput. This paper presents an energy-efficient wireless network system enhanced by UAVs acting as Aerial BSs. We have introduced a Deep Reinforcement Learning (DRL) based Deep Deterministic Policy Gradient (DDPG) mechanism for optimal resource allocation with the twin goals of energy efficiency and average throughput maximization. Through extensive simulations, we validate the performance of our DDPG approach, demonstrating that it outperforms other baseline methods in energy efficiency and throughput maximization.