arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.23618eess.SP
收藏

基于集合变换器的无源一体化感知与通信波束成形设计

Set Transformer-Based Beamforming Design for Cell-Free Integrated Sensing and Communication

Southern Illinois University(南伊利诺伊大学);University of Alberta(阿尔伯塔大学)

Ranga Kulathunga, Diluka Galappaththige, Gayan Aruma Baduge, Chintha Tellambura

AI总结:

本文提出基于集合变换器的无源一体化感知与通信波束成形框架,通过注意力机制建模全局关系,提升分布式接入点、通信用户和感知目标间的交互能力,实现无监督学习,支持三种设计模式,实验表明其在计算效率和性能上均优于传统方法。

摘要:

现有无源一体化感知与通信(CF-ISAC)波束成形算法主要依赖经典优化技术,往往具有高计算复杂度和有限的可扩展性。同时,近期基于学习的方法在捕捉分布式接入点(APs)、通信用户和感知目标间的全局交互和长程依赖方面存在困难。为解决这些限制,我们提出首个基于集合变换器的CF-ISAC波束成形框架(STCIB)。通过利用注意力机制,STCIB显式建模网络实体间的全局关系,自然处理无序输入集,并在APs、用户和目标之间保持排列不变性。所提框架以无监督方式运行,无需标注训练数据,并支持三种设计模式:(i)感知导向型,(ii)通信导向型,(iii)联合ISAC优化。我们通过卷积神经网络(CNN)基线和两种最新优化算法:凸-凹程序算法(CCPA)和增广拉格朗日流形优化(ALM-MO)进行基准测试。数值结果表明,STCIB在CNN上表现更优,仅小幅增加运行时间即可实现显著更高的ISAC性能。例如,在模式(iii)中,当η=0.4时,STCIB相比CNN,感知和通信总速率分别提高14.8%和31.6%,而运行时间仅增加0.26%。与CCPA和ALM-MO相比,STCIB在计算成本上显著降低,同时保持适度的性能提升。在模式(i)中,对于3.0 bps/Hz通信阈值,STCIB的运行时间仅为CCPA和ALM-MO的0.1%和0.3%,同时感知总速率分别提高4.45%和5.9%。

英文摘要:

Existing cell-free integrated sensing and communication (CF-ISAC) beamforming algorithms predominantly rely on classical optimization techniques, which often entail high computational complexity and limited scalability. Meanwhile, recent learning-based approaches have difficulty capturing the global interactions and long-range dependencies among distributed access points (APs), communication users, and sensing targets. To address these limitations, we propose the first Set Transformer-based CF-ISAC beamforming framework (STCIB). By exploiting attention mechanisms, STCIB explicitly models global relationships among network entities, naturally handles unordered input sets, and preserves permutation invariance across APs, users, and targets. The proposed framework operates in an unsupervised manner, eliminating the need for labeled training data, and supports three design regimes: (i) sensing-centric, (ii) communication-centric, and (iii) joint ISAC optimization. We benchmark STCIB against a convolutional neural network (CNN) baseline and two state-of-the-art optimization algorithms: the convex-concave procedure algorithm (CCPA) and augmented Lagrangian manifold optimization (ALM-MO). Numerical results demonstrate that STCIB consistently outperforms the CNN, achieving substantially higher ISAC performance with only a negligible increase in runtime. For instance, in regime (iii), at $η$=0.4, STCIB improves the sensing and communication sum rates by 14.8 % and 31.6 %, respectively, relative to the CNN, while increasing runtime by only 0.26 %. Compared with CCPA and ALM-MO, STCIB offers significantly lower computational cost while maintaining modest performance gains. In regime (i), for a 3.0 bps/Hz communication threshold, the runtime of STCIB is only 0.1 % and 0.3 % of that required by CCPA and ALM-MO, respectively, while improving the sensing sum rate by 4.45 % and 5.9 %.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑