loading page

Deep-Reinforcement Learning for Trajectory Design of Multiple UAV-aided Access Points in Presence of Mobile Users
  • Nipun Agarwal
Nipun Agarwal
Birla Institute of Technology and Science, Birla Institute of Technology and Science

Corresponding Author:[email protected]

Author Profile

Abstract

Next generation communication networks promise seamless connectivity. This mandates high user coverage. Determining optimal access point locations is essential to maximize the total user coverage. However, users are mobile in real-time. Deployment of unmanned aerial vehicle access points (UAPs) has been proposed to improve the coverage. However, the onboard battery in UAPs pose energy limitations. This paper derives the UAP trajectory with optimal energy planning using a deep reinforcement learning approach.