Q-learning-based secure routing protocol for uav ad hoc networks constrained by comprehensive trust

LIU Yanan; SHU Yun; ZHANG Zheng; QIU Shuo; SHEN Jipeng; WANG Pengfei; CANG Jiyun

doi:10.11959/j.issn.1000-0801.DXKX260235

Chinese

您当前的位置：

首页 >

文章列表页 >

Q-learning-based secure routing protocol for uav ad hoc networks constrained by comprehensive trust

更新时间：2026-06-23

- Q-learning-based secure routing protocol for uav ad hoc networks constrained by comprehensive trust
- Telecommunications Science (2026)
- 作者机构：
  
  1.金陵科技学院网络安全学院，江苏南京 211169
  2.河南通达电缆股份有限公司，河南洛阳 471999
  3.东南大学网络空间安全学院，江苏南京 211189
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61902163);the Qing Lan Project of Jiangsu Higher Education Institutions;Henan Province Postdoctoral Research Projects
- DOI：10.11959/j.issn.1000-0801.DXKX260235
  CLC： TP393
- Received：16 April 2026，
  
  Revised：2026-05-31，
  
  Accepted：23 June 2026，
- 稿件说明：
移动端阅览
LIU Yanan, SHU Yun, ZHANG Zheng, et al. Q-learning-based secure routing protocol for uav ad hoc networks constrained by comprehensive trust[J/OL]. Telecommunications Science, 2026.
DOI：

LIU Yanan, SHU Yun, ZHANG Zheng, et al. Q-learning-based secure routing protocol for uav ad hoc networks constrained by comprehensive trust[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260235.

摘要

针对无人机自组网中自私节点易进入转发路径，进而导致传输可靠性下降的问题，提出了基于综合信任约束的Q-learning安全路由协议。该协议面向多跳数据汇聚场景，利用直接信任、间接信任、能量信任和负载信任构建综合信任模型，并采用CRITIC权重法实现动态赋权。在此基础上，节点根据综合信任值形成可信候选邻居集合，再结合Q-learning实现逐跳路由决策。仿真结果表明，该协议能够有效减少自私节点对路由过程的干扰，提高分组投递率，降低端到端时延。说明该协议能够为高动态无人机自组网中的安全稳定传输提供有效支持。

Abstract

To address the problem that selfish nodes in unmanned aerial vehicle ad hoc networks could easily enter forwarding paths

thereby degrading transmission reliability

a Q-learning-based secure routing protocol with comprehensive trust constraints was proposed. For multi-hop data aggregation scenarios

a comprehensive trust model was constructed by integrating direct trust

indirect trust

energy trust

and load trust

and dynamic weighting was achieved by using the CRITIC weighting method. On this basis

a trusted candidate neighbor set was formed according to the comprehensive trust value

and hop-by-hop routing decisions were made in combination with Q-learning. Simulation results showed that the proposed protocol effectively reduced the interference of selfish nodes with the routing process

improved packet delivery ratio

and decreased end-to-end delay. The protocol is effective in supporting secure and reliable transmission in highly dynamic unmanned aerial vehicle ad hoc networks.

关键词

Keywords

references

OGUNBUNMI S , CHEN Y , BLASCH E , et al . A survey on reputation systems for UAV networks [J ] . Drones , 2024 , 8 ( 6 ): 253 .

GONG Y , CHEN Y , LI K , et al . DSCR: A dynamic secure clustering routing scheme for UANETs based on reputation mechanism [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 10 ): 14109 - 14123 .

LUO H , WU Y , SUN G , et al . ESCM: An efficient and secure communication mechanism for UAV networks [J ] . IEEE Transactions on Network and Service Management , 2024 , 21 ( 3 ): 3124 - 3139 .

KHARJANA M , SAHANA S C , SAHA G . Securing autonomous UAV cluster with blockchain-based threshold key management system utilizing crypto-asset and multisignature [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 7 ): 5765 - 5778 .

KUNDU J , ALAM S , KONER C , et al . Trust-based dynamic leader selection mechanism for enhanced performance in flying ad-hoc networks (FANETs) [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 , 25 ( 12 ): 20616 - 20627 .

HOSSEINZADEH M , MOHAMMED A H , ALENIZI F A , et al . A novel fuzzy trust-based secure routing scheme in flying ad hoc networks [J ] . Vehicular Communications , 2023 , 44 : 100665 .

韩优佳 , 胡黄水 , 姚美琴 . 基于信任感知的无线传感器网络安全路由协议 [J ] . 计算机工程 , 2021 , 47 ( 9 ): 145 - 152 .

HAN Y J , HU H S , YAO M Q . Trust-aware secure routing protocol for wireless sensor networks [J ] . Computer Engineering , 2021 , 47 ( 9 ): 145 - 152 .

孙子文 , 吴平 . 基于信任评估模型的 IWSN 安全路由研究 [J ] . 传感技术学报 , 2019 , 32 ( 6 ): 858 - 865 .

SUN Z W , WU P . Secure routing for IWSN based on a trust evaluation model [J ] . Chinese Journal of Sensors and Actuators , 2019 , 32 ( 6 ): 858 - 865 .

郑浩泽 , 潘巨龙 . 一种基于多因子信任机制的无线传感网络安全路由协议 [J ] . 传感技术学报 , 2024 , 37 ( 8 ): 1395 - 1403 .

ZHENG H Z , PAN J L . A secure routing protocol for wireless sensor networks based on a multi-factor trust mechanism [J ] . Chinese Journal of Sensors and Actuators , 2024 , 37 ( 8 ): 1395 - 1403 .

崔颖 , 李巧珏 , 高山 , 等 . 基于改进最小生成树的三维路由算法 [J ] . 应用科技 , 2023 , 50 ( 6 ): 76 - 81 .

CUI Y , LI Q J , GAO S , et al . Three-dimensional routing algorithm based on improved minimum spanning tree [J ] . Applied Science and Technology , 2023 , 50 ( 6 ): 76 - 81 .

党元章 , 华翔 , 张金金 , 等 . 自适应ANP-CRITIC的无人机集群网络优化算法 [J ] . 西安工业大学学报 , 2023 , 43 ( 6 ): 568 - 577 .

DANG Y Z , HUA X , ZHANG J J , et al . UAV swarm network optimization algorithm based on adaptive ANP-CRITIC [J ] . Journal of Xi'an Technological University , 2023 , 43 ( 6 ): 568 - 577 .

HUTCHINS C . Using contextual reinforcement learning to design FANET defence protocols to combat grey hole attacks [C ] // Proceedings of the 2024 IEEE Network Operations and Management Symposium (NOMS) . Piscataway : IEEE Press , 2024 : 1 - 4 .

ZHOU Z , TANG J , YANG Z , et al . A new predictive based secure geographic routing strategy for UAV network under location spoofing attack [J ] . Chinese Journal of Aeronautics , 2025 , 38 ( 10 ): 103498 .

HUSSAIN A , AHMAD W . Delay and energy aware routing (DEAR) protocol for UAV networks [J ] . ICCK Transactions on Intelligent Unmanned Systems , 2025 , 2 ( 1 ): 1 - 14 .

吴麒 , 左林立 , 丁建 , 等 . 基于Q-learning的自适应链路状态路由协议 [J ] . 重庆邮电大学学报(自然科学版) , 2024 , 36 ( 5 ): 945 - 953 .

WU Q , ZUO L L , DING J , et al . Adaptive link-state routing protocol based on Q-learning [J ] . Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition) , 2024 , 36 ( 5 ): 945 - 953 .

谭周正 , 范琅 , 李宇峰 , 等 . 基于强化学习的无人机网络自适应QoS路由算法 [J ] . 计算机应用研究 , 2025 , 42 ( 4 ): 1177 - 1184 .

TAN Z Z , FAN L , LI Y F , et al . Adaptive QoS routing algorithm of UAV network based on reinforcement learning [J ] . Application Research of Computers , 2025 , 42 ( 4 ): 1177 - 1184 .

赵蓓英 , 姬伟峰 , 翁江 , 等 . 基于启发式Q学习的FANET可信路由算法 [J ] . 计算机工程 , 2022 , 48 ( 5 ): 162 - 169 .

ZHAO B Y , JI W F , WENG J , et al . Trusted routing algorithm based on heuristic Q-learning for FANET [J ] . Computer Engineering , 2022 , 48 ( 5 ): 162 - 169 .

刘星宇 , 强楠楠 , 付银娟 . 面向无人机多状态模糊推理的Q学习路由机制研究 [J ] . 信息技术 , 2025 ( 6 ): 17 - 22, 29 .

LIU X Y , QIANG N N , FU Y J . Study on Q-learning routing mechanism for UAVs using multi-state fuzzy inference [J ] . Information Technology , 2025 ( 6 ): 17 - 22, 29 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Secure relay node selection method based on Q-learning for fog computing in 5G network

A Novel Secure Routing Protocol——Multi-Next Hop Routing Protocl Based on Node Potential

Distributed multi-agent task allocation algorithm based on anonymous hedonic games

Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm

Format-preserving encryption algorithm based on dynamic galois field

Related Author

Jinliang YU

Yuan MENG

M WWAQAS

Lei LIU

Shanshan TU

Hailong1 Ma

Youjun1 Bu

Yanhong Wang

Related Institution

Faculty of Information Technology, Beijing University of Technology

Beijing Key Laboratory of Trusted Computing

Department of Electronics and Engineering, Tsinghua University

Beijing Electro-Mechanical Engineering Institute

National Digital Switching System Engineering ＆Technological Center

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰