Unmanned aerial vehicle group-oriented sensing communication integrated network multi-resource joint scheduling method

By constructing a heterogeneous graph structure and a hierarchical multi-agent reinforcement learning architecture, the problem of insufficient resource scheduling in the UAV-ISAC system in dynamic environments is solved, and efficient collaborative allocation and dynamic response of resources in the integrated perception and communication network of UAV swarms are realized.

CN121751369AActive Publication Date: 2026-03-27JIAXING UNIV
3 Cites 5 Cited by

Patent Information

Application Number
CN202610221899.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-25
Publication Date
2026-03-27
Estimated Expiration
2046-02-25

AI Technical Summary

Technical Problem

Existing UAV-ISAC systems struggle to achieve efficient collaborative allocation of communication and sensing resources in dynamic environments. In particular, traditional static resource scheduling strategies are poorly adaptable in scenarios with rapid node movement and frequent changes in business requirements, severely hindering further improvements in system performance.

Method used

By constructing a heterogeneous graph structure of UAVs, communication users, and sensing targets, and using reinforcement learning methods for adaptive decision-making, a system model for multiple UAV-ISAC tasks is established. The hierarchical multi-agent reinforcement learning architecture is used to solve the joint optimization problem online, realizing resource allocation and trajectory planning. The training process is stabilized by combining experience playback and mini-batch sampling mechanisms.

Benefits of technology

It effectively mitigates the conflict between communication and sensing resources in dynamic environments, improves sensing performance and ensures communication quality, and achieves the optimization effect of maximizing communication rate and minimizing sensing accuracy.

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

Abstract

The invention relates to an unmanned aerial vehicle group-oriented sensing communication integrated network multi-resource joint scheduling method, and belongs to the technical field of wireless communication, and the method comprises the steps: building a system model of multiple UAV-ISAC tasks, and defining a joint optimization problem; extracting spatio-temporal features from the dynamic heterogeneous graph in which the unmanned aerial vehicle, the user and the sensing target are abstracted as nodes and the relationship is abstracted as edges; taking the features as input, and adopting a layered multi-agent reinforcement learning architecture to solve the joint optimization problem on line; in the architecture, resource allocation and trajectory planning actions are generated through cooperation of a central Actor and all unmanned aerial vehicle Actors, and system performance is evaluated by a central Critic; constructing a multi-target weighted reward function, stabilizing a training process by combining experience playback and a Mini-batch sampling mechanism, and updating network parameters in parallel; and obtaining an optimal resource allocation and unmanned aerial vehicle trajectory strategy through training. The sensing performance is improved, the communication quality is guaranteed, and the defects in the aspect of dynamic resource scheduling in the prior art are overcome.
Need to check novelty before this filing date? Find Prior Art