Dynamic coverage path planning of energy optimization in UAV-enabled edge computing networks

Unmanned Aerial Vehicle (UAV)-enabled Base Stations (BS) are flexible and can effectively communicate with ground sensors distributed in the field, which is often used to solve the problem of data acquisition. However, the flight path setting and energy consumption of UAV-enabled BS are difficult to solve. In this paper, Q learning approach has been used to optimize the energy consumption of coverage path planning for UAV-enabled edge computing networks. This network is used to connect the virtual sensor data with the real UAV-enabled BS flight, so that capabilities are provided to the edges. Experiments demonstrate that the proposed algorithm is convergent, and in the same environment, reducing the energy consumption as compared with other state-of-the-art solutions in this area.