High-capacity satellite network is the cornerstone of future space-air-ground integrated networks. However, the satellite uplink transmissions still face critical challenges, including severe path loss, complex multi-user interference, and payload constraints. Recently, Reconfigurable Intelligent Surfaces (RIS) and Fluid Antenna Systems (FAS) have shown promise for satellite communications through their dynamic signal reconfiguration. This paper proposes a multi-RIS-assisted satellite Compact Ultra-Massive Antenna Array (CUMA) architecture for multi-user satellite uplink transmission. Specifically, we deploy multiple RISs on the terrestrial side to separate interfering Line-of-Sight (LoS) channels via optimized phase shifts, and adopt a CUMA receiver on the satellite to further mitigate interference through FAS port selection. To solve a sum-rate maximization problem, we alternately optimize FAS port selection using a Forward-Backward Greedy Selection (FBGS) algorithm and RIS phase shifts based on Fractional Programming (FP). To the best of our knowledge, this is the first work to jointly optimize multi-RIS and CUMA in a satellite uplink context, where strong LoS and extreme path loss fundamentally distinguish the design from terrestrial counterparts. Simulation results confirm the effectiveness of the proposed architecture across frequency bands. At 6 GHz, our scheme achieves 181% and 32% rate gains over fixed antennas and traditional CUMA schemes, respectively, while the gains also reach 138% and 27% at 26 GHz, illustrating superiority in both interference-limited and noise-limited regimes.
Kai Feng, Runke Fan, Tianheng Xu et al.· IEEE Open Journal of the Com...· 0 citations
Root cause localization is critical for ensuring service reliability in cloud-edge collaborative microservice systems. In practical scenarios, multiple microservice systems are often hybrid-deployed on shared infrastructure, which poses three challenges for existing methods. First, concurrent systems generate substantial metric noise that interferes with anomaly detection. Second, the hierarchical dependencies spanning cloud, edge, and terminal layers cannot be accurately represented in Euclidean space. Third, gateway services that aggregate traffic from multiple systems exhibit amplified anomaly signals, leading to systematic false alarms. To address these issues, we propose confidence gated agent root cause localization (CGARCL), a framework that integrates hyperbolic geometry with confidence gated agent reasoning. CGARCL consists of three components. The direction constrained budgeted anomaly detection method incorporates baseline robust scoring and temporal continuity constraints to extract high-quality candidate anomalous nodes from noisy metrics. The hyperbolic constrained spatio-temporal graph attention network employs Poincar’e ball mapping and center-based topology aggregation to accurately encode hierarchical service dependencies and generate initial root cause rankings. The confidence gated reranking agent is activated when the score gap between the top two candidates is small or the top-ranked node matches a victim-prone pattern. It then performs structured prompt reasoning to suppress false alarms and produce a refined ranking. Experiments on three cloud-edge collaborative microservices datasets demonstrate that CGARCL achieves ACC@1 of 62.1%, 70.6%, and 73.4%, outperforming the second best approach by 19.1%, 11.4%, and 9.8%.
Yechen He, Yang Yang, Lanlan Rui et al.· IEEE Transactions on Cogniti...· 0 citations