通信感知一体化系统中的联合波形与相移设计

doi:10.3785/j.issn.1008-973X.2026.04.022

浙江大学学报(工学版)

2026, Vol. 60

Issue (4): 906-914 DOI: 10.3785/j.issn.1008-973X.2026.04.022

电子与信息工程

通信感知一体化系统中的联合波形与相移设计

杨青青1,2(

),唐润朋1,2,彭艺1,2,*(

)

1. 昆明理工大学信息工程与自动化学院，云南昆明 650500
2. 昆明理工大学云南省计算机重点实验室，云南昆明 650500

Joint waveform and phase shift design in integrated sensing and communication systems

Qingqing YANG1,2(

),Runpeng TANG1,2,Yi PENG1,2,*(

)

1. School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2. Yunnan Provincial Key Laboratory of Computer Science, Kunming University of Science and Technology, Kunming 650500, China

全文: PDF(2125 KB) HTML

摘要：

针对如何在可重构智能表面(RIS)辅助通信感知一体化(ISAC)系统中有效提升系统容量的问题，提出RIS单元的不规则拓扑结构以及深度强化学习(DRL)算法. 采用模拟退火算法用于解决不规则RIS的拓扑优化问题，以提高在有限元件数量下的最优空间利用效率. 在感知波束图增益约束下，分别采用Adam优化器结合传统的梯度下降法与基于DRL的方法来解决最小化用户间干扰(MUI)的问题. 具体而言，DRL方案通过深度Q网络(DQN)与近端策略优化(PPO)这2种算法分别处理RIS的离散相移控制和ISAC的恒模波形设计. 仿真结果表明，基于DRL算法的不规则RIS辅助通感一体化系统的加权和速率(WSR)相较传统RIS方案提升了13.3%. DRL算法在抑制恒模波束能量泄漏方面具有更显著的优势，进一步验证了不规则RIS的拓扑设计和DRL算法在通感一体化系统中协同优化的可行性.

关键词： 通信感知一体化(ISAC); 不规则可重构智能表面(RIS); 联合波形设计; 相移矩阵; 深度强化学习(DRL)

Abstract:

An irregular topology of reconfigurable intelligent surface (RIS) elements, combined with deep reinforcement learning (DRL) algorithms, was proposed to enhance the capacity of integrated sensing and communication (ISAC) systems. A simulated annealing algorithm was employed to solve the topological structure optimization problem of irregular RIS, ensuring optimal spatial utilization efficiency under a limited number of elements. Under the constraint of sensing beam pattern gain, multi-user interference (MUI) was minimized by two approaches. The first combined the Adam optimizer with traditional gradient descent. The second relied on DRL, where discrete RIS phase shifts and constant-modulus ISAC waveform design were managed by deep Q-network (DQN) and proximal policy optimization (PPO), respectively. Simulation results indicated that the weighted sum rate (WSR) of the irregular RIS-assisted system optimized by DRL increased by 13.3% compared with the conventional RIS scheme. The DRL algorithm also showed stronger capability in suppressing constant-modulus beam energy leakage. These results confirmed the feasibility of jointly optimizing irregular RIS topology and DRL algorithms in integrated sensing and communication systems.

Key words: integrated sensing and communication (ISAC) irregular reconfigurable intelligent surface (RIS) joint waveform design phase shift matrix deep reinforcement learning (DRL)

收稿日期: 2025-05-14 出版日期: 2026-03-19

CLC:

TN 929.5

基金资助: 国家自然科学基金资助项目 (62461030)；云南省基础研究重点项目 (202401AS070105).

通讯作者: 彭艺 E-mail: 20090119@kust.edu.cn;12309214@kust.edu.cn

作者简介: 杨青青（1981—），女，博士，从事无人机路径规划、智能反射面辅助通信研究. orcid.org/0009-0004-4584-6381. E-mail：20090119@kust.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	杨青青
	唐润朋
	彭艺

引用本文:

杨青青,唐润朋,彭艺. 通信感知一体化系统中的联合波形与相移设计[J]. 浙江大学学报(工学版), 2026, 60(4): 906-914.

Qingqing YANG,Runpeng TANG,Yi PENG. Joint waveform and phase shift design in integrated sensing and communication systems. Journal of ZheJiang University (Engineering Science), 2026, 60(4): 906-914.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2026.04.022 或 https://www.zjujournals.com/eng/CN/Y2026/V60/I4/906

图 1 不规则RIS辅助通信感知一体化系统模型

图 2 深度神经网络(DNN)

图 3 深度强化学习网络架构示意图

表 1 不规则RIS辅助通感一体化系统仿真参数设置

图 4 不同RIS拓扑部署结构下对应的加权和速率图

图 5 不同批量大小下的即时奖励曲线图

图 6 不同传输功率下的即时奖励曲线图

图 7 不同基站传输功率下的平均奖励曲线图

图 8 所提算法在不同量化级别下的多用户干扰变化情况图

图 9 所提算法在不同RIS辅助下的系统加权和速率随基站功率$ {P}_{\mathrm{t}} $变化图

图 10 所提算法在不同RIS辅助下的系统和速率随基站信噪比变化图

图 11 所提算法在不同RIS辅助下的系统加权和速率随RIS元件数量变化图

图 12 不同方案下的基站波束强度图

1	CUI Z, HU J, CHENG J, et al Multi-domain NOMA for ISAC: utilizing the DOF in the delay-Doppler domain[J]. IEEE Communications Letters, 2022, 27 (2): 726- 730 doi: 10.1109/lcomm.2022.3228873
2	PIN TAN D K, HE J, LI Y, et al. Integrated sensing and communication in 6G: motivations, use cases, requirements, challenges and future directions [C]// 1st IEEE International Online Symposium on Joint Communications and Sensing. Dresden: IEEE, 2021: 1–6.
3	WU 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
4	虞湘宾, 于凯, 钱盼盼面向6G移动通信的可重构智能反射表面技术研究综述[J]. 南京航空航天大学学报, 2023, 55 (5): 745- 756 YU Xiangbin, YU Kai, QIAN Panpan Overview of reconfigurable intelligent surface for 6G mobile communication[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2023, 55 (5): 745- 756 doi: 10.16356/j.1005-2615.2023.05.001
5	DI B, ZHANG H, SONG L, et al Hybrid beamforming for reconfigurable intelligent surface based multi-user communications: achievable rates with limited discrete phase shifts[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (8): 1809- 1822 doi: 10.1109/JSAC.2020.3000813
6	NASSAR F, SINGH K, PRAKRIYA S, et al. Robust beamformer design for backscatter-enabled RIS-assisted NOMA ISAC [C]// IEEE International Conference on Communications Workshops. Denver: IEEE, 2024: 608–613.
7	CHEN J, WU K, NIU J, et al Spectral and energy efficient waveform design for RIS-assisted ISAC[J]. IEEE Transactions on Communications, 2025, 73 (1): 158- 172 doi: 10.1109/TCOMM.2024.3435030
8	ZHANG S, XIAO Z, LIU R, et al Multipath exploitation for fluctuating target detection in RIS-assisted ISAC systems[J]. IEEE Wireless Communications Letters, 2024, 13 (9): 2392- 2396 doi: 10.1109/LWC.2024.3416453
9	CHEN K, QI C, DOBRE O A, et al Simultaneous beam training and target sensing in ISAC systems with RIS[J]. IEEE Transactions on Wireless Communications, 2024, 23 (4): 2696- 2710 doi: 10.1109/TWC.2023.3302319
10	LYU W, XIU Y, YANG S, et al Energy-efficient cell-free network assisted by hybrid RISs[J]. IEEE Wireless Communications Letters, 2023, 12 (4): 718- 722 doi: 10.1109/LWC.2023.3241644
11	ZHU Q, LI M, LIU R, et al Cramér-Rao bound optimization for active RIS-empowered ISAC systems[J]. IEEE Transactions on Wireless Communications, 2024, 23 (9): 11723- 11736 doi: 10.1109/TWC.2024.3384501
12	ZHU Q, LI M, LIU R, et al Joint transceiver beamforming and reflecting design for active RIS-aided ISAC systems[J]. IEEE Transactions on Vehicular Technology, 2023, 72 (7): 9636- 9640 doi: 10.1109/TVT.2023.3249752
13	ZHANG Y, REN H, PAN C, et al Secure wireless communication in active RIS-assisted DFRC systems[J]. IEEE Transactions on Vehicular Technology, 2025, 74 (1): 626- 640 doi: 10.1109/TVT.2024.3438151
14	褚宏云, 杨梦瑶, 黄航, 等混合智能反射面辅助的通信感知一体化: 高能效波束成形设计[J]. 电子与信息学报, 2024, 46 (6): 2462- 2469 CHU Hongyun, YANG Mengyao, HUANG Hang, et al Hybrid reconfigurable intelligent surface assisted integrated sensing and communication: energy efficient beamforming design[J]. Journal of Electronics and Information Technology, 2024, 46 (6): 2462- 2469 doi: 10.11999/JEIT230699
15	SU R, DAI L, TAN J, et al Capacity enhancement for reconfigurable intelligent surface-aided wireless network: from regular array to irregular array[J]. IEEE Transactions on Vehicular Technology, 2023, 72 (5): 6392- 6403 doi: 10.1109/TVT.2023.3236179
16	EL-MEADAWY S A, ZHU P, KHALLAF H S Multilayer irregular RIS-assisted wireless communication system performance optimization[J]. IEEE Internet of Things Journal, 2025, 12 (1): 931- 949
17	LIU Q, ZHU Y, LI M, et al DRL-based secrecy rate optimization for RIS-assisted secure ISAC systems[J]. IEEE Transactions on Vehicular Technology, 2023, 72 (12): 16871- 16875 doi: 10.1109/TVT.2023.3297602
18	ZHU Z, GONG M, CHU Z, et al. DRL-based STAR-RIS-assisted ISAC secure communications [C]// International Conference on Ubiquitous Communication. Xi’an: IEEE, 2023: 127–132.
19	MOHAMMED S K, LARSSON E G Per-antenna constant envelope precoding for large multi-user MIMO systems[J]. IEEE Transactions on Communications, 2013, 61 (3): 1059- 1071 doi: 10.1109/TCOMM.2013.012913.110827
20	LIU F, ZHOU L, MASOUROS C, et al Toward dual-functional radar-communication systems: optimal waveform design[J]. IEEE Transactions on Signal Processing, 2018, 66 (16): 4264- 4279 doi: 10.1109/TSP.2018.2847648
21	STOICA P, LI J, XIE Y On probing signal design for MIMO radar[J]. IEEE Transactions on Signal Processing, 2007, 55 (8): 4151- 4161 doi: 10.1109/TSP.2007.894398
22	HU C, DAI L, HAN S, et al Two-timescale channel estimation for reconfigurable intelligent surface aided wireless communications[J]. IEEE Transactions on Communications, 2021, 69 (11): 7736- 7747 doi: 10.1109/TCOMM.2021.3072729
23	KIRKPATRICK S, GELATT C D Jr, VECCHI M P Optimization by simulated annealing[J]. Science, 1983, 220 (4598): 671- 680 doi: 10.1126/science.220.4598.671
24	HAJEK B Cooling schedules for optimal annealing[J]. Mathematics of Operations Research, 1988, 13 (2): 311- 329 doi: 10.1007/978-1-4612-4808-8_42
25	SHI Y, YANG K, JIANG T, et al Communication-efficient edge AI: algorithms and systems[J]. IEEE Communications Surveys and Tutorials, 2020, 22 (4): 2167- 2191 doi: 10.1109/COMST.2020.3007787

[1]	周围,窦文静,李倩倩,徐锐. 基于置信度和期望传播的GSM-OTFS信号检测算法[J]. 浙江大学学报(工学版), 2024, 58(12): 2609-2618.
[2]	胡浪涛,杨瑞,黄崇文,刘全金,吴磊,谭镇坤. RIS辅助双功能雷达与隐蔽通信系统性能优化[J]. 浙江大学学报(工学版), 2023, 57(12): 2533-2543.
[3]	陈俊杰,李洪均,朱晓军. 采用Benders分解的5G核心网用户面动态部署算法[J]. 浙江大学学报(工学版), 2023, 57(3): 625-631.
[4]	容志能,金文光,骆一希. 人体运动传感数据的无线采集方案设计[J]. J4, 2012, 46(7): 1314-1319.
[5]	求钦龙,吴春明, 平玲娣,吕红兵. 重传TCP确认包及在长期演进网络中的应用[J]. J4, 2011, 45(9): 1509-1515.
[6]	赵仙红,杨俊,赵利民. 新的幅值扰动形成零陷算法[J]. J4, 2011, 45(1): 64-67.
[7]	陈勋, 张朝阳, 罗海燕. 无线Mesh网络中功率控制、信道分配和调度的联合优化[J]. J4, 2009, 43(8): 1406-1411.

Viewed

Full text

Abstract

Cited

Shared

Discussed