Ranga Kulathunga | Searcharxiv

arXiv2026

Reconfigurable Intelligent Surfaces for Cognitive Radio Networks: Design, Optimization, and Emerging Trends

Reconfigurable intelligent surfaces (RISs) enable programmable wireless propagation environments, offering new opportunities for cognitive radio networks (CRNs) to improve spectrum utilization, enhance spectral and energy efficiency, and operate reliably under low signal-to-noise ratio conditions. By combining the complementary strengths of RISs and CRNs, RIS-assisted CRNs (RCNs) have emerged as a promising architecture for future 6G wireless systems. Despite their growing importance, a comprehensive survey of this rapidly evolving field has been lacking. This paper fills this gap by providing a systematic and comprehensive review of RCNs. The paper first introduces the fundamentals of CRNs and RISs, including dynamic spectrum access models, spectrum sensing techniques, RIS operating principles, and RIS architectures. It then examines the design of RCNs, covering their system architectures, deployment strategies, channel estimation, spectrum access mechanisms, communication protocols, and the joint optimization of RIS and CRN parameters. Next, the existing literature is organized into six major research directions: performance analysis, resource allocation and optimization, secure RCNs, active RISs, simultaneously transmitting and reflecting RISs, and machine learning-enabled RCNs. Finally, the paper discusses key research challenges and future directions, including scalability, practical deployment, integration with emerging 6G technologies, coexistence with evolving network architectures, standardization, and security and privacy. This survey provides a unified reference for researchers and practitioners and establishes a roadmap for the future development of RCNs.

eess.SP↗

arXiv2026

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

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 $\eta$=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 %.

eess.SP↗