Optimized deployment of multi-UAV based on machine learning in UAV-HST networking

A new communications infrastructure is needed for users to experience the contents of 5G-based VR/AR in High-Speed Train (HST). Therefore, it is proposed that the Unmanned Aerial Vehicle (UAV) can be used as a communication equipment on behalf of the general Rail-side Units (RSUs) supporting the communication of the HST. To maintain reliable communications, initial deployment and trajectory considered altitude and direction of UAV are determined. Also, limited energy in UAV is an important constraint on trajectory optimization. Thus, this paper proposes initial deployment and trajectory optimization techniques for stable communication between HST and Multi-UAV with the energy constraints of UAV. This paper uses Soft Actor-Critic (SAC), one of the methods of reinforcement learning, as a way to optimize the UAV trajectory. It also uses the Support Vector Machine to carry out optimal initial deployment based on data on the maximum UAV communication distance according to the speed of HST and the energy of UAV, which is the result of trajectory optimization. As a result, this study quickly and accurately derives the optimal trajectory of Multi-Uav according to the speed of HST and the energy of UAV and also maintain stable communication by optimal initial deployment.