The evolution of sixth-generation (6G) networks increasingly demands seamless and reliable connectivity across heterogeneous and geographically dispersed environments, with maritime regions remaining a major challenge due to vast coverage areas, limited terrestrial infrastructure, and complex propagation conditions. In this paper, we investigate the capacity characteristics of space-air-ground-sea integrated networks (SAGSINs) for maritime communications. Specifically, we consider a SAGSIN system comprising a terrestrial base station (BS), a geostationary satellite, a decode-and-forward (DF) relay, and maritime users randomly distributed according to a Poisson point process (PPP). The relay, implemented by either an uncrewed aerial vehicle (UAV) or a large ship, serves multiple maritime users, providing a unified framework for comparing heterogeneous relay platforms and backhaul options. Based on this model, the system performance is analyzed under two representative fading regimes: 1) quasi-static fading, where analytical expressions and tight upper bounds are derived for the outage probability and corresponding outage capacity; and 2) block fading, where closed-form ergodic capacity formulations are obtained to evaluate the long-term average throughput. Extensive Monte Carlo simulations validate the theoretical analysis and quantify the effects of key system parameters. Our results offer insights into the design and optimization of high-reliability maritime communication links, providing guidelines for practical implementation and future 6G SAGSINs development.
Jinpeng Xu, Yingqi He, Lin Zhou et al.· IEEE Transactions on Wireles...· 0 citations
The evolution of uncrewed aerial vehicles (UAVs) into embodied intelligent agents in the low-altitude economy is reshaping edge computing networks. However, the high mobility of UAVs induces severe topology dynamics, limiting the efficacy of traditional fully connected multiagent reinforcement learning because of dimensionality and credit assignment challenges. Furthermore, existing graph attention approaches neglect explicit communication boundary constraints, leading to mismatches between value evaluation and physical topology. To address these challenges, this paper proposes the spatial-aware graph attention multiagent twin delayed deep deterministic policy gradient (SAGA-MATD3) algorithm. By embedding a dynamic spatial masking mechanism based on the communication radius into the critic network, the proposed method enforces physical reachability constraints and attenuates extraneous noise. Simulation results demonstrate that SAGA-MATD3 significantly reduces service latency and improves fairness under an acceptable energy-consumption tradeoff, achieving a 37.1% improvement in convergence reward and enabling the self-organization of robust load-balanced mesh topologies.
Ye Wang, Jingjing Wang, Jianrui Chen et al.· IEEE Transactions on Cogniti...· 0 citations
The evolution of sixth-generation (6G) networks increasingly necessitates seamless and on-demand coverage across heterogeneous environments, particularly maritime regions where traditional terrestrial infrastructure is limited. In this paper, we aim to enhance the quality of service (QoS) for maritime users in the 6G space-air-sea integrated networks (SASINs). To shed light on the design of SASIN, we consider a communication model consisting of a single satellite, a single decode-and-forward (DF) uncrewed aerial vehicle (UAV) relay, and multiple maritime users. A novel on-demand coverage performance metric, service efficiency, is proposed to evaluate the QoS of maritime users. Particularly, in order to explore the boundary performance of the proposed architecture, both uplink and downlink communications are analyzed under the assumption of perfect channel state information (CSI). Furthermore, we formulate optimization problems to maximize the service efficiency for both uplink and downlink transmissions, subject to the user scheduling and decoding order, beamforming design, and placement of the relay UAV, respectively. To address the uplink optimization problems, we propose an alternating optimization (AO) algorithm that integrates a greedy randomized adaptive search procedure (GRASP)-based user scheduling algorithm with a successive convex approximation (SCA)-based UAV placement strategy to obtain a high-quality suboptimal solution. Analogously, for the downlink optimization problem, we develop an AO algorithm that combines a low-complexity greedy user scheduling scheme based on an initial beamforming design with the joint optimization of UAV placement and beamforming, effectively balancing performance and computational efficiency. Finally, extensive numerical results demonstrate that the proposed schemes achieve near-optimal performance with significantly reduced complexity, offering a strong solution for high-efficiency SASIN in future 6G maritime communications.
Yingqi He, Jinpeng Xu, Lin Zhou et al.· IEEE Transactions on Wireles...· 0 citations