UAV-BSs energy and service priority trajectory design method based on double-Q learning

Abstract

The invention belongs to the technical field of unmanned aerial vehicle (UAV) trajectory design, and particularly relates to a UAV-BSs energy and service priority trajectory design method based on double-Q learning, which comprises the following steps: modeling a ground service area into a grid, setting a state space, creating a self position, a node position and each node service priority by a UAV, and regarding the UAV as a Q-Learning model; by the UAV, continuously performing data interaction with the node equipment in a flight process and updating an algorithm function according to an interaction return; and performing effect comparison by using an Epsilon-Greedy algorithm and a Double Q-Learning algorithm, so as to realize trajectory optimization. According to the method, the flight path of the UAV is optimized by using Double Q-Learning so as to reduce energy consumption, and meanwhile, services are provided for a request node according to the required service priority, so that the Q-Learning-based flight path is superior to a reference node service algorithm, namely a Greedily-served algorithm, in the aspects of reducing the average energy consumption of the UAV-BSs and improving the priority node service delay; therefore, the practicability of the system is enhanced. The method is used for designing the UAV-BSs trajectory.

Description

technical field [0001] The invention belongs to the technical field of UAV trajectory design, in particular to a UAV-BSs energy and service priority trajectory design method based on double-Q learning. Background technique [0002] Next-generation mobile networks propose the integration of unmanned aerial vehicles as aerial base stations (UAV-BSs) serving ground nodes, and despite the advantages of using UAV-BSs, their reliance on on-board, limited-capacity batteries hampers their continuity of service , shorter flight trajectories can save flight energy, but since the service requirements of nodes are not always the same, UAV-BSs must also serve nodes according to their service priorities, in an unmanned system oriented to the Internet of Things In the aircraft-assisted node priority, the trajectory of UAV-BSs is designed to minimize the flight cost while providing services to nodes according to the priority. Therefore, an intelligent model is needed that UAV-BSs can use in...

AI Technical Summary

Problems solved by technology

[0003] Problems or deficiencies of existing techniques: Currently, the trajectory design of UAV-BSs is optimized using the traveling salesman problem approach to improve energy efficiency, but the applicability of TSP is also limited in cases where service priority must be considered

Images