融合Q-learning的低空无人机集群通信链路自适应调度研究
Research on Adaptive Scheduling of Low altitude UAV Cluster Communication Link Integrating Q-learning
杨锦涛 1王昕1
作者信息
- 1. 辽宁工程技术大学电子与信息工程学院，葫芦岛 125000
- 折叠
摘要
随着低空经济的快速发展，无人机在应急通信、环境监测和物流运输等领域得到广泛应用。低空无人机自组网由于具有节点高速移动、网络拓扑动态变化频繁以及通信链路不稳定等特点，传统自组网路由协议在复杂动态环境中的性能受到一定限制。为提高低空无人机网络的通信效率与资源利用率，本文提出一种基于Q-learning的低空无人机自组网资源调度与路由优化方法。首先构建低空无人机自组网系统模型，分析节点通信与资源分配特性；其次将Q-learning算法引入路由决策过程，通过构建包含节点剩余能量、节点间距离以及队列长度等因素的状态空间，并设计综合奖励函数，实现对下一跳节点的智能选择与网络资源的动态调度；最后通过仿真实验对所提出算法进行性能评估，并与传统AODV和OLSR路由协议进行对比分析。仿真结果表明，该方法在数据包投递率、平均时延和能量利用效率等指标上优于AODV和OLSR协议，适用于高动态低空无人机自组网场景。
Abstract
With the rapid development of the low-altitude economy, unmanned aerial vehicles (UAVs) have been widely applied in emergency communication, environmental monitoring, and logistics transportation. Due to the characteristics of high-speed node movement, frequent dynamic changes in network topology, and unstable communication links, the performance of traditional ad hoc network routing protocols is limited in complex and dynamic environments. To improve the communication efficiency and resource utilization of low-altitude UAV networks, this paper proposes a resource scheduling and routing optimization method for low-altitude UAV ad hoc networks based on Q-learning. Firstly, a low-altitude UAV ad hoc network system model is constructed, and the communication and resource allocation characteristics of nodes are analyzed. Secondly, the Q-learning algorithm is introduced into the routing decision process. By constructing a state space that includes factors such as the remaining energy of nodes, the distance between nodes, and the queue length, and designing a comprehensive reward function, the intelligent selection of the next-hop node and the dynamic scheduling of network resources are achieved. Finally, the performance of the proposed algorithm is evaluated through simulation experiments and compared with traditional AODV and OLSR routing protocols. The experimental results show that the proposed algorithm exhibits better performance in terms of packet delivery ratio, average delay, and network energy utilization, effectively enhancing the overall communication efficiency of low-altitude UAV ad hoc networks. The research results can provide certain references for intelligent routing and resource management in low-altitude UAV networks.关键词
低空无人机网络/自组网/Q-learning/资源调度/路由优化Key words
Low-altitude unmanned aerial vehicle (UAV) network/Ad hoc network/Q-learning/Resource scheduling/Routing optimization引用本文复制引用
杨锦涛,王昕.融合Q-learning的低空无人机集群通信链路自适应调度研究[EB/OL].(2026-05-15)[2026-05-18].http://www.paper.edu.cn/releasepaper/content/202605-80.学科分类
无线通信/航空航天技术
评论