基于鲁棒深度强化学习的IRS辅助分散计算网络保密速率和优化

李嘉欣; 王建萍; 刘之滨; 林福宏

doi:10.12263/DZXB.20260219

您当前的位置：

首页 >

文章列表页 >

基于鲁棒深度强化学习的IRS辅助分散计算网络保密速率和优化

更新时间：2026-06-09

- 基于鲁棒深度强化学习的IRS辅助分散计算网络保密速率和优化
- Secure Sum Rate and Optimization in IRS-Assisted Dispersed Computing Network Based on Robust Deep Reinforcement Learning
- 电子学报 2026年页码：1-12
- 作者机构：
  
  1.北京科技大学计算机与通信工程学院，北京100083
  2.国家电网有限公司华北分部，北京，100053
- 作者简介：
  
  [ "李嘉欣女，1995年8月出生于山西省朔州市。现为北京科技大学计算机与通信工程学院博士研究生。主要研究方向为多接入边缘计算和人工智能。 E-mail: b20200318@xs.ustb.edu.cn" ]
  [ "王建萍女，1974年1月出生于河北省保定市。现为北京科技大学计算机与通信工程学院通信工程系教授。主要研究方向为可见光通信、人工智能。 E-mail: jpwang@ustb.edu.cn" ]
  [ "刘之滨男，1985年2月出生于北京市。现为中国国家电网公司华北分公司高级工程师。主要研究方向为网络安全、数字化管理和计算机网络。 E-mail: liu.zbin@nc.sgcc.com.cn" ]
  [ "林福宏男，1981年11月出生于山西省朔州市。现为北京科技大学计算机与通信工程学院通信工程系教授。主要研究方向为网络安全、人工智能和边缘/雾计算。 E-mail: fhlin@ustb.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62436004);国家重点研发计划基金资助项目(2022YFB3104903)
- DOI：10.12263/DZXB.20260219
  中图分类号： TN929.5;
- 收稿：2026-03-11，
  
  录用：2026-05-16，
  
  网络首发：2026-06-09，
- 稿件说明：
移动端阅览
李嘉欣, 王建萍, 刘之滨, 等. 基于鲁棒深度强化学习的IRS辅助分散计算网络保密速率和优化[J/OL]. 电子学报, 2026,1-12.

LI Jiaxin, WANG Jianping, LIU Zhibin, et al. Secure Sum Rate and Optimization in IRS-Assisted Dispersed Computing Network Based on Robust Deep Reinforcement Learning[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-12.
李嘉欣, 王建萍, 刘之滨, 等. 基于鲁棒深度强化学习的IRS辅助分散计算网络保密速率和优化[J/OL]. 电子学报, 2026,1-12. DOI： 10.12263/DZXB.20260219.

LI Jiaxin, WANG Jianping, LIU Zhibin, et al. Secure Sum Rate and Optimization in IRS-Assisted Dispersed Computing Network Based on Robust Deep Reinforcement Learning[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-12. DOI： 10.12263/DZXB.20260219.

摘要

为解决恶劣无线通信环境下分散计算网络中高保密传输和高服务质量（Quality of Service，QoS）的协同需求，本文提出了一种智能反射面（Intelligent Reconfigurable Surface，IRS）辅助的分散计算网络保密通信与资源优化方案。首先，由于分散计算网络中的无人机（Unmanned Aerial Vehicle，UAV）节点受到自身能源的限制，本文研究了一种新颖的能量收集（Energy Harvesting，EH）方案，通过在几何空间上对IRS被动反射阵列进行功能划分，使部分反射单元用于信息反射，部分单元用于EH，从而实现信息传输与能量采集的协同进行。其次，构建了IRS辅助分散计算网络中的保密速率和最大化优化模型。该模型通过联合优化用户发射功率、IRS反射元件相移、EH约束以及通信QoS等多个耦合变量，以提升系统整体保密性能和资源利用效率。由于优化问题具有高度非凸性和变量强耦合特性，传统优化方法难以直接获得全局最优解。此外，考虑到分散计算网络中用户移动性强、无线信道动态变化快以及环境状态不确定等特点，本文设计了一种基于鲁棒深度强化学习（Deep Reinforcement Learning，DRL）的动态资源优化算法，以在动态分散计算网络环境中保证QoS。仿真结果表明：所提出的基于鲁棒DRL的IRS辅助分散计算网络方案性能不仅优于现有的其他基于学习的解决方案，还接近穷举法性能，最终验证了所提方案的有效性和优越性。

Abstract

To address the collaborative requirements of high-security transmission and high quality of service (QoS) in dispersed computing network under harsh wireless communication environments

this paper proposes a secure communication and resource optimization scheme for intelligent reconfigurable surface (IRS)-assisted dispersed computing network. Firstly

due to the energy limitations of unmanned aerial vehicle (UAV) nodes

this paper studies a novel energy harvesting (EH) scheme. By dividing the IRS passive reflection array in geometric space

some reflection elements are used for information reflection

and some elements are used for EH

so as to realize the cooperation of information transmission and EH. Secondly

the secure sum rate maximization optimization model in IRS-assisted dispersed computing network is formulated. The model jointly optimizes multiple coupling variables such as user transmission power

IRS reflection element phase shift

EH constraint and communication QoS

while improve the overall system security performance and resource utilization efficiency. Since the formulated optimization problem is highly non-convex and the variables are strongly coupled

traditional optimization methods are difficult to directly obtain the global optimal solution. Furthermore

considering the characteristics of dispersed computing network

such as high user mobility

rapidly varying wireless channels

and uncertain environmental states

a robust deep reinforcement learning (DRL)-based dynamic resource optimization algorithm is designed to guarantee QoS in dynamic dispersed computing environments. Simulation results show that the performance of the IRS-assisted dispersed computing network scheme based on robust DRL proposed in this paper not only outperforms existing learning-based solutions but also achieves performance close to that of the exhaustive search method

verifying the effectiveness and superiority of the proposed scheme.

关键词

Keywords

references

Karaman B , Basturk I , Taskin S , et al . Solutions for sustainable and resilient communication infrastructure in disaster relief and management scenarios [J ] . IEEE Communications Surveys & Tutorials , 2026 , 28 : 716 - 760 . DOI: 10.1109/comst.2025.3610793 http://dx.doi.org/10.1109/comst.2025.3610793

Wu H J , Zhang J , Cai Z P , et al . Resolving multitask competition for constrained resources in dispersed computing: A bilateral matching game [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 23 ): 16972 - 16983 . DOI: 10.1109/jiot.2021.3075673 http://dx.doi.org/10.1109/jiot.2021.3075673

Liu Y W , Liu X , Mu X D , et al . Reconfigurable intelligent surfaces: Principles and opportunities [J ] . IEEE Communications Surveys & Tutorials , 2021 , 23 ( 3 ): 1546 - 1577 . DOI: 10.1109/comst.2021.3077737 http://dx.doi.org/10.1109/comst.2021.3077737

Ning Z , Li T , Wu Y , et al . 6G Communication new paradigm: The integration of unmanned aerial vehicles and intelligent reflecting surfaces [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 6 ): 3382 - 3416 . DOI: 10.1109/comst.2025.3526251 http://dx.doi.org/10.1109/comst.2025.3526251

Zhang J F , Wang W , Tang J , et al . Robust secure transmission for IRS-aided NOMA networks with hybrid beamforming [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 4 ): 3086 - 3101 . DOI: 10.1109/twc.2023.3305406 http://dx.doi.org/10.1109/twc.2023.3305406

Lv L , Zhao S , Zhou Y N , et al . Secure transmission for dual-function IRS-assisted cognitive radio NOMA networks [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 8 ): 10768 - 10782 . DOI: 10.1109/jiot.2024.3513414 http://dx.doi.org/10.1109/jiot.2024.3513414

Wang Z , Wu W , Zhou F H , et al . IRS-enhanced spectrum sensing and secure transmission in cognitive radio networks [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 8 ): 10271 - 10286 . DOI: 10.1109/twc.2024.3370812 http://dx.doi.org/10.1109/twc.2024.3370812

Li Z , Zhang L J , Le S W , et al . Distributed modulation exploiting IRS for secure communications [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 10 ): 11193 - 11208 . DOI: 10.1109/tmc.2025.3579960 http://dx.doi.org/10.1109/tmc.2025.3579960

Bao J Y , Cao Y , Qin X Q , et al . Secure constructive interference precoding for IRS-aided NOMA networks [J ] . IEEE Transactions on Wireless Communications , 2025 , 24 ( 12 ): 10296 - 10310 . DOI: 10.1109/twc.2025.3578729 http://dx.doi.org/10.1109/twc.2025.3578729

Pandey G K , Gurjar D S , Yadav S , et al . UAV-assisted communications with RF energy harvesting: A comprehensive survey [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 2 ): 782 - 838 . DOI: 10.1109/comst.2024.3425597 http://dx.doi.org/10.1109/comst.2024.3425597

Ponnimbaduge Perera T D , Jayakody D N K , Sharma S K , et al . Simultaneous wireless information and power transfer (SWIPT): Recent advances and future challenges [J ] . IEEE Communications Surveys & Tutorials , 2018 , 20 ( 1 ): 264 - 302 . DOI: 10.1109/comst.2017.2783901 http://dx.doi.org/10.1109/comst.2017.2783901

Song H H , Wen H , Tang J , et al . Secrecy energy efficiency maximization for distributed intelligent-reflecting-surface-assisted MISO secure communications [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 5 ): 4462 - 4474 . DOI: 10.1109/jiot.2022.3218664 http://dx.doi.org/10.1109/jiot.2022.3218664

Li B G , Liao J , Wu W J , et al . Intelligent reflecting surface assisted secure computation of wireless powered MEC system [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 4 ): 3048 - 3059 . DOI: 10.1109/tmc.2023.3269791 http://dx.doi.org/10.1109/tmc.2023.3269791

Zhang J F , Xu J L , Lu W D , et al . Secure transmission for IRS-aided UAV-ISAC networks [J ] . IEEE Transactions on Wireless Communications , 2024 , 23 ( 9 ): 12256 - 12269 . DOI: 10.1109/twc.2024.3390169 http://dx.doi.org/10.1109/twc.2024.3390169

Xu J L , Zhang J F , Liu M Q , et al . Secure integrated sensing and SWIPT via active IRS [J ] . IEEE Transactions on Wireless Communications , 2025 , 24 ( 8 ): 6997 - 7011 . DOI: 10.1109/twc.2025.3557410 http://dx.doi.org/10.1109/twc.2025.3557410

Dong J W , Wang F . PIRS and ASTAR-IRS jointly aided wireless communications using RSMA: Deployment design and rate allocations [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 5 ): 5575 - 5588 . DOI: 10.1109/jiot.2024.3487762 http://dx.doi.org/10.1109/jiot.2024.3487762

Wang H D , Zhao S H , Li L H , et al . Learning joint source-channel encoding in IRS-assisted multi-user semantic communications [C ] // 2025 IEEE International Symposium on Parallel and Distributed Processing with Applications . Piscataway : IEEE , 2025 : 15 - 20 . DOI: 10.1109/ispa67752.2025.00012 http://dx.doi.org/10.1109/ispa67752.2025.00012

Khan A , Hayat B , Ahmad S , et al . AI-empowered multi-UAV and IRS collaboration for spectrum and energy optimization in B5G networks [J ] . IEEE Internet of Things Journal , 2026 , 13 ( 5 ): 7972 - 7988 . DOI: 10.1109/jiot.2025.3601983 http://dx.doi.org/10.1109/jiot.2025.3601983

Wu Q Q , Zhang R . Joint active and passive beamforming optimization for intelligent reflecting surface assisted SWIPT under QoS constraints [J ] . IEEE Journal on Selected Areas in Communications , 2020 , 38 ( 8 ): 1735 - 1748 . DOI: 10.1109/jsac.2020.3000807 http://dx.doi.org/10.1109/jsac.2020.3000807

Wan Z X , Jiang W H , Nie J T , et al . Min-max fairness based joint optimal design for IRS-assisted MEC systems [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 8 ): 11949 - 11963 . DOI: 10.1109/tvt.2024.3377434 http://dx.doi.org/10.1109/tvt.2024.3377434

Al-Hourani A , Kandeepan S , Jamalipour A . Modeling air-to-ground path loss for low altitude platforms in urban environments [C ] // 2014 IEEE Global Communications Conference . Piscataway : IEEE , 2014 : 2898 - 2904 . DOI: 10.1109/glocom.2014.7037248 http://dx.doi.org/10.1109/glocom.2014.7037248

Lei M , Zhang X J , Yu B C , et al . Throughput maximization for UAV-assisted wireless powered D2D communication networks with a hybrid time division duplex/frequency division duplex scheme [J ] . Wireless Networks , 2021 , 27 ( 3 ): 2147 - 2157 . DOI: 10.1007/s11276-021-02562-w http://dx.doi.org/10.1007/s11276-021-02562-w

Xiong X , Zheng B X , Swindlehurst A L , et al . A new intelligent reflecting surface-aided electromagnetic stealth strategy [J ] . IEEE Wireless Communications Letters , 2024 , 13 ( 5 ): 1498 - 1502 . DOI: 10.1109/lwc.2024.3378455 http://dx.doi.org/10.1109/lwc.2024.3378455

Wu Q Q , Zhang R . Beamforming optimization for wireless network aided by intelligent reflecting surface with discrete phase shifts [J ] . IEEE Transactions on Communications , 2020 , 68 ( 3 ): 1838 - 1851 . DOI: 10.1109/tcomm.2019.2958916 http://dx.doi.org/10.1109/tcomm.2019.2958916

Hu G J , Wu Q Q , Xu D H , et al . Intelligent reflecting surface-aided wireless communication with movable elements [J ] . IEEE Wireless Communications Letters , 2024 , 13 ( 4 ): 1173 - 1177 . DOI: 10.1109/lwc.2024.3364147 http://dx.doi.org/10.1109/lwc.2024.3364147

Luo C , Hu J , Xiang L P , et al . Massive wireless energy transfer without channel state information via imperfect intelligent reflecting surfaces [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 6 ): 8529 - 8541 . DOI: 10.1109/tvt.2024.3361210 http://dx.doi.org/10.1109/tvt.2024.3361210

Tang Y Z , Ma G G , Xie H L , et al . Joint transmit and reflective beamforming design for IRS-assisted multiuser MISO SWIPT systems [C ] // 2020 IEEE International Conference on Communications . Piscataway : IEEE , 2020 : 1 - 6 . DOI: 10.1109/icc40277.2020.9148892 http://dx.doi.org/10.1109/icc40277.2020.9148892

Yu X H , Xu D F , Sun Y , et al . Robust and secure wireless communications via intelligent reflecting surfaces [J ] . IEEE Journal on Selected Areas in Communications , 2020 , 38 ( 11 ): 2637 - 2652 . DOI: 10.1109/jsac.2020.3007043 http://dx.doi.org/10.1109/jsac.2020.3007043

Li X L , Huo J H , Huangfu W , et al . Secrecy sum rate maximization in UAV-IRS assisted networks with credit-aware cooperative multi-agent reinforcement learning [J ] . IEEE Transactions on Wireless Communications , 2026 , 25 : 3186 - 3200 . DOI: 10.1109/twc.2025.3602188 http://dx.doi.org/10.1109/twc.2025.3602188

Peng H R , Wang L C . Energy harvesting reconfigurable intelligent surface for UAV based on robust deep reinforcement learning [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 10 ): 6826 - 6838 . DOI: 10.1109/twc.2023.3245820 http://dx.doi.org/10.1109/twc.2023.3245820

Peng H R , Tsai A H , Wang L C , et al . LEOPARD: Parallel optimal deep echo state network prediction improves service coverage for UAV-assisted outdoor hotspots [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 1 ): 282 - 295 . DOI: 10.1109/tccn.2021.3115765 http://dx.doi.org/10.1109/tccn.2021.3115765

Bellman R . A Markovian decision process [J ] . Indiana University Mathematics Journal , 1957 , 6 ( 4 ): 679 - 684 . DOI: 10.1512/iumj.1957.6.56038 http://dx.doi.org/10.1512/iumj.1957.6.56038

Mnih V , Badia A P , Mirza M , et al . Asynchronous methods for deep reinforcement learning [C ] // International Conference on Machine Learning . New York : PMLR , 2016 : 1928 - 1937 .

Lillicrap T P , Hunt J J , Pritzel A , et al . Continuous control with deep reinforcement learning [PP/OL ] . V6. arXiv ( 2019-07-05 )[ 2026-03-11 ] . https://doi.org/10.48550/arXiv.1509.02971 https://doi.org/10.48550/arXiv.1509.02971 .

Mnih V , Kavukcuoglu K , Silver D , et al . Human-level control through deep reinforcement learning [J ] . Nature , 2015 , 518 ( 7540 ): 529 - 533 . DOI: 10.1038/nature14236 http://dx.doi.org/10.1038/nature14236

Fujimoto S , Hoof H , Meger D . Addressing function approximation error in actor-critic methods [C ] // International conference on machine learning . Stockholm : PMLR , 2018 : 1587 - 1596 . DOI: 10.48550/arXiv.1802.09477 http://dx.doi.org/10.48550/arXiv.1802.09477

Hasselt H . Double Q-learning [C ] // Proceedings of the 24th Annual Conference on Neural Information Processing Systems . Vancouver : Curran Associates, Inc. , 2010 : 2613 - 2621 .

Pan L , Cai Q , Huang L . Softmax deep double deterministic policy gradients [J ] . Advances in neural information processing systems , 2020 , 33 : 11767 - 11777 .

Lai C C , Chen C T , Wang L C . On-demand density-aware UAV base station 3D placement for arbitrarily distributed users with guaranteed data rates [J ] . IEEE Wireless Communications Letters , 2019 , 8 ( 3 ): 913 - 916 . DOI: 10.1109/lwc.2019.2899599 http://dx.doi.org/10.1109/lwc.2019.2899599

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

电磁干扰对IRS辅助短包通信的影响

基于多域表征对齐融合的雷达目标无监督异常检测方法

执行器攻击下开放式异构多智能体系统的自适应输出一致性

面向类别不平衡ECG的快速患者间域适应心律失常识别方法

结合频域物理感知与高阶语义融合的一体化遥感图像复原框架