Energy Consumption Reduction for UAV Trajectory Training: A Transfer Learning Approach

The advent of 6G technology demands flexible, scalable wireless architectures to support ultra-low latency, high connectivity, and high device density. The Open Radio Access Network (O-RAN) framework, with its open interfaces and virtualized functions, provides a promising foundation for such architectures. However, traditional fixed base stations alone are not sufficient to fully capitalize on the benefits of O-RAN due to their limited flexibility in responding to dynamic network demands. The integration of Unmanned Aerial Vehicles (UAVs) as mobile RUs within the O-RAN architecture offers a solution by leveraging the flexibility of drones to dynamically extend coverage. However, UAV operating in diverse environments requires frequent retraining, leading to significant energy waste. We proposed transfer learning based on Dueling Double Deep Q network (DDQN) with multi-step learning, which significantly reduces the training time and energy consumption required UAVs to adapt to new environments. We designed simulation environments and conducted ray tracing experiments using Wireless InSite with real-world map data. In the two simulated environments, training energy consumption was reduced by 30.52% and 58.51%, respectively. Furthermore, tests on real-world maps of Ottawa and Rosslyn showed energy reductions of 44.85% and 36.97%, respectively.