RIS-assisted MIMO active and passive beamforming design based on multi-armed bandit

Shen Tianze; Wang Ge; Song Yunchao; Gao Tianbao; Liang Huibin

doi:10.11959/j.issn.1000-0801.2026008

您当前的位置：

首页 >

文章列表页 >

RIS-assisted MIMO active and passive beamforming design based on multi-armed bandit

Research and Development | 更新时间：2026-03-05

- RIS-assisted MIMO active and passive beamforming design based on multi-armed bandit
- Telecommunications Science Vol. 42, Issue 2, Pages: 45-58(2026)
- 作者机构：
  
  南京邮电大学电子与光学工程学院、柔性电子（未来技术）学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  The General Program of the National Natural Science Foundation of China(62371249)
- DOI：10.11959/j.issn.1000-0801.2026008
  CLC： TN928
- Received：04 April 2025，
  
  Revised：2025-07-03，
  
  Accepted：06 August 2025，
  
  Published：20 February 2026
- 稿件说明：
移动端阅览
沈天泽,汪革,宋云超等.基于多臂赌博机的RIS辅助MIMO主被动波束成形设计[J].电信科学,2026,42(02):45-58.

Shen Tianze,Wang Ge,Song Yunchao,et al.RIS-assisted MIMO active and passive beamforming design based on multi-armed bandit[J].Telecommunications Science,2026,42(02):45-58.
沈天泽,汪革,宋云超等.基于多臂赌博机的RIS辅助MIMO主被动波束成形设计[J].电信科学,2026,42(02):45-58. DOI： 10.11959/j.issn.1000-0801.2026008.

Shen Tianze,Wang Ge,Song Yunchao,et al.RIS-assisted MIMO active and passive beamforming design based on multi-armed bandit[J].Telecommunications Science,2026,42(02):45-58. DOI： 10.11959/j.issn.1000-0801.2026008.

摘要

可重构智能表面（reconfigurable intelligent surface，RIS）因其低功耗、易调节、辅助通信等优势，被广泛应用于毫米波通信领域，现有大多数传输方案利用信道状态信息设计预编码和RIS的被动波束成形矩阵，然而，这将消耗较大的导频开销，导致频谱效率下降。基于此，利用多臂赌博机（multi-armed bandit，MAB）算法进行RIS辅助多输入多输出（multiple-input multiple-output，MIMO）系统的波束成形设计，该算法从历史数据中获取信道协方差矩阵，并用于波束成形设计，以降低导频开销。具体来说，将被动波束成形矩阵设计问题建模为MAB问题，结合线性上置信界（linear upper confidence bound，LinUCB）算法框架来估计信道协方差矩阵，将有效频谱效率设置为奖励、RIS相移向量设置为动作，提出利用层级贪婪搜索算法选择最大化有效频谱效率之和的方法获取相移向量。仿真结果表明，所提出的算法在减少导频开销、提高有效频谱效率方面表现良好，展示了其优越性。

Abstract

Reconfigurable intelligent surface (RIS) has gained significant attention in millimeter-wave communications due to its advantages

including low power consumption

easy tunability

and enhanced auxiliary communication capabilities. Most existing transmission schemes employ channel state information to design precoding and passive beamforming matrices for RIS. However

this approach incurs substantial pilot overhead

thereby reducing spectral efficiency. To address this issue

a beamforming design scheme for RIS-assisted multiple-input multiple-output (MIMO) systems based on the multi-armed bandit (MAB) algorithm was proposed. The channel covariance matrix was estimated using historical data via the MAB framework

which helped to reduce pilot overhead. Specifically

the passive beamforming matrix design was formulated as an MAB problem and solved using the linear upper confidence bound (LinUCB) algorithm to estimate the channel covariance matrix. The effective spectral efficiency was defined as the reward

while the RIS phase shift vector constitutes the action. The phase shift vector that maximizes the sum of effective spectral efficiency was selected through a hierarchical greedy search algorithm. Simulation results demonstrate that the proposed algorithm effectively reduces pilot overhead and enhances spectral efficiency

thereby confirming its superiority.

关键词

Keywords

references

Andrews J G , Buzzi S , Choi W , et al . What will 5G be? [J ] . IEEE Journal on Selected Areas in Communications , 2014 , 32 ( 6 ): 1065 - 1082 .

Al-Shuwaili A , Zaki N D , Abed G S , et al . Channel characterization for RIS-enabled indoor mmWave communications [C ] // Proceedings of the 2022 3rd Information Technology To Enhance e-learning and Other Application (IT-ELA) . Piscataway : IEEE Press , 2022 : 89 - 93 .

Wang R Z , Ren H , Pan C H , et al . Channel estimation for RIS-aided mmWave massive MIMO system using few-bit ADCs [J ] . IEEE Communications Letters , 2023 , 27 ( 3 ): 961 - 965 .

Dash S P , Kaushik A . RIS-assisted 6G wireless communications: a novel statistical framework in the presence of direct channel [J ] . IEEE Communications Letters , 2024 , 28 ( 3 ): 717 - 721 .

朱路虎 , 王安定 . 一种基于ADMM的多用户联合的RIS信道估计方案 [J ] . 电信科学 , 2024 , 40 ( 12 ): 74 - 85 .

Zhu L H , Wang A D . Multi-user joint RIS channel estimation based on ADMM [J ] . Telecommunications Science , 2024 , 40 ( 12 ): 74 - 85 .

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 .

Dai J X , Zhang S L , Zhi K D , et al . Two-timescale design for simultaneous transmitting and reflecting RIS-assisted massive MIMO systems with imperfect CSI [J ] . IEEE Transactions on Communications , 2024 , 72 ( 7 ): 4287 - 4304 .

Basar E , Di Renzo M , De Rosny J , et al . Wireless communications through reconfigurable intelligent surfaces [J ] . IEEE Access , 2019 , 7 : 116753 - 116773 .

Zhang Z J , Dai L L . Reconfigurable intelligent surfaces for 6G: nine fundamental issues and one critical problem [J ] . Tsinghua Science and Technology , 2023 , 28 ( 5 ): 929 - 939 .

Chen J C . Joint transceiver and intelligent reflecting surface design for mmWave massive MIMO systems [J ] . IEEE Systems Journal , 2023 , 17 ( 1 ): 792 - 803 .

Di Renzo M , Danufane F H , Tretyakov S . Communication models for reconfigurable intelligent surfaces: from surface electromagnetics to wireless networks optimization [J ] . Proceedings of the IEEE , 2022 , 110 ( 9 ): 1164 - 1209 .

Wu Q Q , Zhang R . Intelligent reflecting surface enhanced wireless network via joint active and passive beamforming [J ] . IEEE Transactions on Wireless Communications , 2019 , 18 ( 11 ): 5394 - 5409 .

Luo H H , Liu R , Li M , et al . Joint beamforming design for RIS-assisted integrated sensing and communication systems [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 12 ): 13393 - 13397 .

He Z Q , Yuan X J . Cascaded channel estimation for large intelligent metasurface assisted massive MIMO [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 2 ): 210 - 214 .

Zhao M M , Wu Q Q , Zhao M J , et al . Intelligent reflecting surface enhanced wireless networks: two-timescale beamforming optimization [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 1 ): 2 - 17 .

Cao Y S , Lv T J , Ni W . Two-timescale optimization for intelligent reflecting surface-assisted MIMO transmission in fast-changing channels [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 12 ): 10424 - 10437 .

Zhi K D , Pan C H , Ren H , et al . Two-timescale design for reconfigurable intelligent surface-aided massive MIMO systems with imperfect CSI [J ] . IEEE Transactions on Information Theory , 2023 , 69 ( 5 ): 3001 - 3033 .

Sutton R S . Reinforcement learning: an introduction [M ] . Cambridge, Massachusetts : MIT Press , 1998 .

Qian M , Li C , Ma Y , et al . A Contextual MAB-based two-timescale scheme for RIS-assisted systems [J ] . IEEE Wireless Communications Letters , 2025 , 14 ( 2 ): 400 - 404 .

Ayach O E , Rajagopal S , Abu-Surra S , et al . Spatially sparse precoding in millimeter wave MIMO systems [J ] . IEEE Transactions on Wireless Communications , 2014 , 13 ( 3 ): 1499 - 1513 .

Minn H , Al-Dhahir N . Optimal training signals for MIMO OFDM channel estimation [J ] . IEEE Transactions on Wireless Communications , 2006 , 5 ( 5 ): 1158 - 1168 .

Yang H , Marzetta T L . Performance of conjugate and zero-forcing beamforming in large-scale antenna systems [J ] . IEEE Journal on Selected Areas in Communications , 2013 , 31 ( 2 ): 172 - 179 .

Lattimore T , SzepesváRi C . Bandit algorithms [M ] . Cambridge : Cambridge University Press , 2020 : 75 - 83 .

El Jaghaoui S , Elmiad A K , Lmah A B . Enhancing the traveling salesman problem solutions with reinforcement learning: a variant exploration-exploitation approach beyond ε-Greedy [C ] // Proceedings of 2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA) . Casablanca, Morocco : IEEE , 2023 : 1 - 6 .

Li L , Chu W , Langford J , et al . A contextual-bandit approach to personalized news article recommendation [C ] // Proceedings of the 19th International Conference on World Wide Web . Raleigh, North Carolina, USA : ACM , 2010 : 661 - 670 .

Wang H , Fang J , Duan H , et al . Spatial channel covariance estimation and two-timescale beamforming for IRS-assisted millimeter wave systems [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 9 ): 6048 - 6060 .

Su Y , Xiong D , Wan Y , et al . LinFuzz: program-sensitive seed scheduling Greybox fuzzing based on LinUCB algorithm [J ] . IEEE Access , 2024 , 12 : 74843 - 74860 .

Chen J , Zhao L , Jiang M , et al . Sherman-morrison formula aided adaptive channel estimation for underwater visible light communication with fractionally-sampled OFDM [J ] . IEEE Transactions on Signal Processing , 2020 , 68 : 2784 - 2798 .

So A M C , Zhang J , Ye Y . On approximating complex quadratic optimization problems via semidefinite programming relaxations [J ] . Mathematical Programming , 2007 , 110 ( 1 ): 93 - 110 .

Wang P , Fang J , Wu Z , et al . Two-timescale beamforming for IRS-assisted millimeter wave systems: a deep unrolling-based stochastic optimization approach [C ] // Proceedings of 2022 IEEE 12th Sensor Array and Multichannel Signal Processing Workshop (SAM) . Trondheim, Norway : IEEE , 2022 : 191 - 195 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Performance optimization on RIS-assisted communication for anti-jamming

Physical layer security of MIMO wireless systems with adaptive modulation

Spatial channel modeling for MIMO underwater wireless optical links

A Survey of Interference Suppression in Femtocell Network

Related Author

LI Qiang

MA Junyu

LI Yapeng

GE Xiaohu

Guangqiu LI

Hui LI

Yancui LUO

Huizhi LIU

Related Institution

School of Electronic Information and Communications, Huazhong University of Science and Technology

Shenzhen International Graduate School, Tsinghua University

Pengcheng Laboratory

College of Computer, Nanjing University of Posts and Telecommunications

College of IoT, Nanjing University of Posts and Telecommunications

⁰