Resource allocation and trajectory planning method of unmanned aerial vehicle data acquisition system based on non-orthogonal multiple access assistance

By adopting non-orthogonal multiple access-assisted resource allocation and trajectory planning methods in the drone data acquisition system, using neural networks and deep reinforcement learning algorithms, the problem that traditional technology is difficult to meet the communication resource limitations of a large number of sensor access is solved, and more efficient data acquisition and lower latency are achieved.

CN119767266AActive Publication Date: 2025-04-04ARMY ENG UNIV OF PLA
5 Cites 0 Cited by

Patent Information

Application Number
CN202411711671.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-27
Publication Date
2025-04-04
Estimated Expiration
2044-11-27

AI Technical Summary

Technical Problem

In drone data acquisition systems, traditional orthogonal multiple access is difficult to meet the communication resource limitations of a large number of sensor access, and deep reinforcement learning is difficult to effectively solve the non-convex optimization problem.

Method used

The resource allocation and trajectory planning method of the drone data acquisition system based on non-orthogonal multiple access assistance is adopted. By decomposing and optimizing the problem, the trajectory planning neural network and channel allocation neural network are used, and the channel allocation neural network is combined with the near-end gradient optimization algorithm and the deep reinforcement learning algorithm are used to optimize the channel allocation and trajectory planning of the drone.

Benefits of technology

It effectively shortens the completion time of drone data acquisition tasks, improves spectrum utilization, and reduces the latency of the receiver.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a resource allocation and trajectory planning method of an unmanned aerial vehicle data acquisition system based on non-orthogonal multiple access assistance. Under the condition of ensuring complete data acquisition and considering the speed of the unmanned aerial vehicle, a three-dimensional track, channel allocation of sensor nodes and access time slot length, an optimization problem of shortest task acquisition time of the unmanned aerial vehicle is designed, and a DRL algorithm based on rolling baseline and near-end gradient optimization combination is designed for an H-NOMA channel allocation problem, so that the algorithm efficiency is improved. For the same DSAC trajectory optimization algorithm, the completion time of the RPPO channel allocation algorithm provided by the invention is shorter; according to the invention, a distributed DSAC algorithm is designed, and the DSAC trajectory optimization algorithm provided by the invention is shorter in completion time. The RPPO algorithm and the DSAC algorithm adopted by the invention can realize optimization of acquisition task time in the unmanned aerial vehicle-NOMA data acquisition system with dynamic channel access, and the task time is lower than that of a reference method.
Need to check novelty before this filing date? Find Prior Art