In the large-scale dynamic Low Earth Orbit (LEO) satellite networks, the conventional TCP-based single-path transmission encounters challenges such as prolonged propagation delay, frequent connection failures, and suboptimal resource utilization. In this paper, we propose an Integrated Multi-Path Network Coding (IMPNC) transmission scheme. This scheme leverages multiple paths for end-to-end transmission to achieve bandwidth aggregation and redundant backup. The multi-path transmission is facilitated by Multi-Path Quick UDP Internet Connection (MPQUIC) protocol to adapt to the limited satellite bandwidth and caching resources. The proposed approach involves encoding packets at nodes along the paths, addressing the significant out-of-order problem arising from variable delays on different paths. Additionally, we present a Software Defined Networking (SDN)-based domain clustering architecture, which offers a more streamlined control approach, reducing overall complexity. Furthermore, we formulate the domain clustering problems as mixed-integer nonlinear programming and the coding-based routing problem as a Steiner tree problem. Evaluation results demonstrate that the proposed scheme effectively reduces the latency over 25.1%, enhances bandwidth utilization by 19.6%, and ensures reliable data transmission by reducing retransmission probability by 4.1%.

Recently, MEC has been integrated with satellite networks to process remote terrestrial computation tasks with superior coverage and delay. Since single satellite computation is hard to tackle spatially uneven computation workloads, computation peer offloading among multiple satellites is urgently needed to further improve service quality and resource utilization. However, considering limited resources, deficient energy, and costly overheads of communication and computation, how to enable efficient offloading cooperation in the time-varying satellite networks is a significant challenge. In this paper, we first design a satellite peer offloading scheme, where offloading is performed along multi-hop paths to explore collaborative computing capabilities. Second, we formulate the Multi-Hop Satellite Peer offloading (MHSPO) problem, aiming to jointly minimize the delay and energy consumption under system resources and backlog constraints. Then, to adapt to the network dynamics, the decision-making process with uncertain future workloads is optimized by leveraging the delayed online learning method under the Lyapunov framework. Finally, we develop a practical online distributed algorithm to solve the MHSPO problem, which is proven to achieve close-to-optimal performance. Extensive simulations show that multi-hop peer offloading among satellites improves edge computing performance efficiently.

360-degree videos have gained considerable popularity by offering immersive experiences to viewers. However, they consume significantly high bandwidth and demand for specialized caching schemes at the edge network. Previous caching schemes are limited as they either rely on complete historical data or neglect the viewer-varying characteristics in 360-degree videos. In this paper, we present an online caching scheme for 360-degree videos that leverages feedback from sequentially arriving viewers at the network edge. Our scheme consists of two components: an online tile popularity prediction component that accurately predicts the popularity of the tiles with the PopPred algorithm, and an online tile-bitrate caching optimization component that optimizes caching decisions to enhance viewers’ quality of experience (QoE) with the CacheOpt algorithm. We prove that both algorithms have sublinear regret, i.e., $O(\sqrt K ),$ where K is the number of viewers. We also conduct comprehensive experiments using real-world data to show that our caching scheme achieves better performance with lower regrets, higher QoE, and higher hit ratios compared with existing algorithms.

The natural mesh network topology of satellite networks makes multi-path transmission prevalent due to its ability to provide bandwidth aggregation and backup using redundant paths. While as one of the significant benefits of multi-path transmission, high reliability requires extensive signaling to achieve excellent performance. So designing an analysis and treatment method to tackle the network overhead and reliability balance remains a major challenge. In addition, massive and burst services in satellite networks will have different demands, which require the network to execute fine-grained path scheduling and management of the multi-path transmission. In this paper, we carefully model the multi-path reliability and network overhead factors under the SDN-based integrated satellite-terrestrial network architecture to characterize the network state. Second, an adaptive multi-path selection scheme is designed to handle the number of active paths, which considers different Quality of Service (QoS) requirements under the limited resources of satellite networks. Then, we formulate the problem as Non-Linear Binary Programming (NLBP) and develop a practical Particle Swarm Optimization (PSO)-based algorithm to solve it. Simulation results show that the proposed scheme can improve satellite networks’ throughput and resource utilization.

With digitization and globalization in the era of 5G and beyond, research on high-throughput satellites (HTS) to increase communication capacity and improve flexibility is becoming essential. To achieve efficient resource utilization and dynamic traffic demand matching, the multi-dimensional resource management (MDRM) problem of the HTS communication system has been studied in this paper. Since the MDRM problem is a non-convex mixed integer problem, we decompose it into two tractable sub-problems. First, the beam-domain resource configuration problem is formed to enable on-demand coverage. Next, the user-domain resource allocation problem is modeled to enable on-demand communication. Considering the two-domain optimization problem, a two-stage framework is developed based on the combination of self-supervised learning and deep reinforcement learning. Specifically, in the first stage, a maximum co-channel interference based self-supervised learning method is proposed to perform traffic demand matching through demand awareness. In the second stage, a soft frequency reuse based proximal policy optimization approach is presented to further increase the system capacity through interference coordination. The simulation results demonstrate that our proposed two-stage algorithm outperforms the benchmark schemes in terms of spectrum efficiency and demand satisfaction.

Data center networks include a wide variety of service categories, which leads to a complex network topology. As a result, the QoS of different service flows cannot be guaranteed. In this paper, we propose a QoS assurance mechanism based on P4 switches (P4SQA) to make full use of network resources. P4SQA includes two functions: in-network traffic classification and in-network queue management. To reduce the communication overhead and computational pressure on the Software Defined Network (SDN) controller, we offload part of the neural computation from the control plane to the data plane. A fully connected neural network-based traffic classification method is deployed in the programmable data plane to classify different traffic types. In addition, the optimized active queue management algorithm CoDeL is integrated into the P4 switch (PCoDeL) to prevent network congestion while guaranteeing QoS more effectively. The evaluation results show that traffic classification accuracy has improved, especially in terms of the F1_score, which reached 0.97, significantly better than other state-of-the-art methods. Moreover, compared to traditional queue management algorithms, PCoDeL can improve network throughput and reduce transmission delay, which verifies the effectiveness and superiority of P4SQA in ensuring QoS.