Satellite networks are emerging as core infrastructure for sixth-generation (6G) wireless systems, yet they face stringent constraints on bandwidth, onboard energy, processing capability, and link availability that bit-oriented communication cannot resolve. Semantic communication, which extracts and transmits task-relevant meaning rather than raw bits, offers a principled remedy across the satellite stack. This survey provides a layered overview of satellite semantic communication, covering: (i) the physical layer with channel-aware joint source-channel coding (JSCC) under long propagation delay, severe Doppler, and time-varying signal-to-noise ratio (SNR); (ii) onboard semantic processing with lightweight encoders, model compression, and in-orbit edge inference for radiation-hardened payloads; (iii) inter-satellite link (ISL) and network-layer routing, distributed federated learning across constellations, and 3rd Generation Partnership Project (3GPP) non-terrestrial network (NTN) integration; and (iv) representative applications spanning Earth observation (EO), satellite Internet of Things (IoT), direct-to-device (D2D), and deep-space scenarios. We synthesize quantitative gains across orbital regimes, identify open challenges in security, standardization, and heterogeneous-orbit interoperability, and outline directions including foundation-model compression, neuromorphic onboard computing, and carbon-aware orchestration for sustainable space connectivity.
Tung Son Do, Thanh Phung Truong, The-Vi Nguyen et al.· International Conference on...· 0 citations
As the transition toward sixth-generation (6G) wireless networks accelerates, the demand for ultra-low latency and high energy efficiency has become paramount. Traditional Mobile Edge Computing (MEC) frameworks face significant challenges in highly dynamic and interference-limited environments. This survey explores a synergistic architectural framework that integrates Fluid Antenna Systems (FAS), Reconfigurable Intelligent Surfaces (RIS), and Hybrid Non-Orthogonal Multiple Access (NOMA)-MEC to address these requirements. We investigate how FAS-enabled port selection enhances channel disparity for optimized NOMA pairing, while RIS-controlled interference landscapes provide the stability necessary for robust Successive Interference Cancellation (SIC) decoding. This comprehensive survey provides a detailed roadmap for future research, highlighting the critical role of programmable physical layers in enabling the next generation of intelligent edge computing systems.
Kiet Nguyen Tuan Tran, Huy Dang Mac, Tung Son Do et al.· International Conference on...· 0 citations
Unmanned aerial vehicle (UAV) communications are a promising enabler for 6G networks, offering flexible deployment and strong line-of-sight channel conditions. Effective UAV operation requires jointly optimizing trajectory and user scheduling to balance throughput and information freshness. This paper proposes a proximal policy optimization (PPO)-based deep reinforcement learning (DRL) framework that controls UAV movement and user scheduling together via a joint MultiDiscrete action space. We formulate a Markov decision process for a 8-user, $1000 \times 1000 \mathrm{~m}^{2}$ service area with a 3GPP TR 36.777-compliant channel model, where the agent selects both its next position and which user to serve at each time slot. The proposed PPO policy achieves 85.75 Mbps mean throughput, a 24.4% improvement over the AoI-greedy baseline, while reducing mean AoI by 87.7% compared to the throughput-greedy baseline, reaching a Pareto-optimal trade-off between the two competing objectives. An ablation study over the AoI penalty weight confirms a clear throughput-AoI trade-off, validating the joint design.
Quang Tuan Do, Tung Son Do, Thanh Phung Truong et al.· International Conference on...· 0 citations