Multi-unmanned aerial vehicle energy-saving cruise communication coverage method based on deep reinforcement learning

Abstract

The invention belongs to the field of space-air-ground integration, and relates to the technical field of multi-unmanned aerial vehicle cruise and unmanned aerial vehicle auxiliary communication, in particular to a multi-unmanned aerial vehicle energy-saving cruise communication coverage method based on deep reinforcement learning. Comprising the following steps: establishing communication between an unmanned aerial vehicle and a ground user, and rasterizing a target area when a ground user communication condition is satisfied; determining a key gathering point area and a common target area in the target area, and setting corresponding weights of the key gathering point area and the common target area respectively; setting related variables and evaluation indexes required in the environment, and performing centralized training and distributed execution on the plurality of unmanned aerial vehicles by adopting a deep reinforcement learning method; and calculating the energy efficiency of the multi-unmanned aerial vehicle cruising coverage target area in the whole network, the average coverage index of the target area and the fair coverage index of the target area. According to the method, communication coverage of the whole area after a disaster can be realized, compared with other methods, the method has better effects on the average coverage index, the fair coverage index and the energy efficiency, and energy conservation and consumption reduction of multi-unmanned aerial vehicle communication are realized while the feasibility of the system is improved.

Description

technical field [0001] The invention belongs to the field of air-space-ground integration, relates to the technical field of multi-UAV coordinated control and UAV-assisted communication, and in particular relates to a multi-UAV energy-saving cruise communication coverage method based on deep reinforcement learning. Background technique [0002] Due to its characteristics of rapid deployment, convenient operation, low cost, large capacity and wide coverage, UAVs are widely used in the field of air-space-ground integration, especially for UAV-assisted communication. In order to provide communication conditions for ground nodes to the greatest extent and save costs, it is necessary to study the energy-saving cruise coverage of multiple UAVs under the conditions of communication. communication. Multi-UAV energy-saving cruise coverage communication mainly involves saving UAV energy consumption and cruising to cover the target area. Multi-UAV cruise coverage of the target area in...

AI Technical Summary

Problems solved by technology

[0003] At present, there has been research on multi-UAV assisted communication based on deep reinforcement learning, but there is still a lack of research on multi-UAV assisted communication based on deep reinforcement learning in the case of complex distribution of ground users.

In addition, in the existing technology, some studies have analyzed the multi-UAV cruise coverage based on ordinary cell division under the communication condition, but there is still a lack of multi-UAV cruise coverage with a certain reward value for the cell under the communication condition.

Images