Stacked intelligent metasurfaces (SIM) provide a low-power means for MIMO transmission and reception using large multi-layer apertures that are digitally controlled. In this letter, we develop a SIM model that is consistent with metasurface theory. We use the Lorentzian function to emulate the amplitude-phase trade-off in meta-atoms. Therefore, realistic hardware impairments are introduced that change the system performance. Then, the general sheet transition conditions (GSTC) map the amplitude-phase trade-off to reflective and transmissive scattering parameters. Since the latter is only applicable to a single layer, we use network theory to extend it to multiple layers yielding an end-to-end SIM system model. Given the new feature, we derive a new Euclidean gradient of the system for optimization. Numerical results show that the ideal model overestimates sum rate by up to 7.5 bps/Hz at deeper configurations and that aperture size should be prioritized over cascade depth in physical SIM design.
Alfredo Gonzalez, Tharmalingam Ratnarajah, Robert W. Heath· IEEE Wireless Communications...· 0 citations
Sixth-generation (6G) networks are moving toward AI-native operation, where learning modules are embedded across the radio access network (RAN), edge, and core. This transition requires learning from limited labels, heterogeneous wireless and network data, partial observations, non-stationary propagation, and latency-constrained control loops. Joint-embedding predictive architecture (JEPA) is a promising self-supervised paradigm for this setting because it predicts missing or future representations in latent space instead of reconstructing raw measurements or using contrastive negative samples. This article presents a wireless-oriented tutorial on JEPA for 6G intelligence. We define the JEPA training mechanism, describe how CSI, beam measurements, KPIs, topology graphs, and sensing observations can be tokenized and masked, and position the learned encoder as a predictive representation layer for RAN, O-RAN, edge, and core functions, with task-specific heads or controllers producing final decisions. Then we present an illustrative, beam-management case study suggesting that a wireless-aware target, specifically an auxiliary future beam-energy target during self-supervised pretraining, can improve label efficiency and robustness across shifted deployment conditions relative to a supervised source domain. Finally, we outline open challenges in multi-timescale prediction, action-conditioned modeling, distributed training, trustworthiness, efficient deployment, benchmarking, and standardization.
Sheikh Salman Hassan, Irshad A. Meer, Almoatssimbillah Saifaldawla et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
