Paper ID: 2202.10338

UAV Base Station Trajectory Optimization Based on Reinforcement Learning in Post-disaster Search and Rescue Operations

Shiye Zhao, Kaoru Ota, Mianxiong Dong

Because of disaster, terrestrial base stations (TBS) would be partly crashed. Some user equipments (UE) would be unserved. Deploying unmanned aerial vehicles (UAV) as aerial base stations is a method to cover UEs quickly. But existing methods solely refer to the coverage of UAVs. In those scenarios, they focus on the deployment of UAVs in the post-disaster area where all TBSs do not work any longer. There is limited research about the combination of available TBSs and UAVs. We propose the method to deploy UAVs cooperating with available TBSs as aerial base stations. And improve the coverage by reinforcement learning. Besides, in the experiments, we cluster UEs with balanced iterative reducing and clustering using hierarchies (BIRCH) at first. Finally, achieve base stations' better coverage to UEs through Q-learning.

Submitted: Feb 17, 2022