Multi-unmanned aerial vehicle cooperative communication Q value table learning method and scheduling method and device

Abstract

The invention provides a Q value table learning method for multi-unmanned aerial vehicle cooperative communication scheduling, a multi-unmanned aerial vehicle cooperative communication scheduling method, a Q value table learning device, electronic equipment and a storage medium. The Q value table learning method comprises the steps of determining an initial Q value table of a current unmanned aerial vehicle, wherein the Q value table records Q values corresponding to different cooperative communication strategies executed by the N unmanned aerial vehicles when the corresponding unmanned aerialvehicle is in each environment state, the different environment states represent different disturbed conditions of the signals of the target frequency band, and each cooperative communication strategy represents a combination of communication strategies of each unmanned aerial vehicle in the N unmanned aerial vehicles; obtaining the Q value tables of other unmanned aerial vehicles except the current unmanned aerial vehicle in the N unmanned aerial vehicles in the Kth time slot; and updating the Q value of the current unmanned aerial vehicle in the Q value table of the Kth time slot through aQ learning mode to obtain the Q value table of the (K + 1) th time slot. The Q value table learning method provided by the invention can improve the overall scheduling success rate of the N unmanned aerial vehicles.

Description

technical field [0001] The present invention relates to the field of unmanned aerial vehicles, and more specifically, relates to a learning method of a Q-value table for multi-UAV cooperative communication scheduling, a multi-UAV cooperative communication scheduling method, a learning device for a Q-value table, electronic equipment and storage medium. Background technique [0002] In recent years, small and low-cost UAV swarms have received widespread attention. Compared with single UAVs, multi-UAV swarms have obvious advantages in flexibility, fault tolerance, collaboration, and task diversity. The application of man-machine cluster is more and more extensive. For example, each UAV in the UAV swarm can act as an access node, as a ground communication station or as a signal repeater for communication equipment. [0003] In the existing technology, the coordinated execution tasks of the drone cluster are commanded and dispatched by the control center, and the control cente...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a learning method of a Q-value table for multi-UAV collaborative communication scheduling, a multi-UAV cooperative communication scheduling method, a learning device for a Q-value table, electronic equipment, and a storage medium to solve the existing multi-UAV cooperative communication scheduling method. In man-machine scheduling technology, each drone cannot make independent decisions based on its own flight environment and the status of other drones, and the overall scheduling success rate of multiple drones is low.

Images