Fast convergence routing is a critical issue for Low Earth Orbit (LEO) constellation networks because these networks have dynamic topology changes, and transmission requirements can vary over time. However, most of the previous research has focused on the Open Shortest Path First (OSPF) routing algorithm, which is not well-suited to handle the frequent changes in the link state of the LEO satellite network. In this regard, we propose a Fast-Convergence Reinforcement Learning Satellite Routing Algorithm (FRL–SR) for LEO satellite networks, where the satellite can quickly obtain the network link status and adjust its routing strategy accordingly. In FRL–SR, each satellite node is considered an agent, and the agent selects the appropriate port for packet forwarding based on its routing policy. Whenever the satellite network state changes, the agent sends “hello” packets to the neighboring nodes to update their routing policy. Compared to traditional reinforcement learning algorithms, FRL–SR can perceive network information faster and converge faster. Additionally, FRL–SR can mask the dynamics of the satellite network topology and adaptively adjust the forwarding strategy based on the link state. The experimental results demonstrate that the proposed FRL–SR algorithm outperforms the Dijkstra algorithm in the performance of average delay, packet arriving ratio, and network load balance.

In the realm of providing space-based internet access services, utilizing large-scale low Earth orbit (LEO) satellite networks have emerged as a promising solution for bridging the digital divide and connecting previously unconnected regions. The deployment of LEO satellites can augment terrestrial networks, with increased efficiency and reduced costs. However, as the size of LEO constellations continues to grow, the routing algorithm design of such networks faces numerous challenges. In this study, we present a novel routing algorithm, designated as Internet Fast Access Routing (IFAR), aimed at facilitating faster internet access for users. The algorithm consists of two main components. Firstly, we develop a formal model that calculates the minimum number of hops between any two satellites in the Walker-Delta constellation, along with the corresponding forwarding direction from source to destination. Then, a linear programming is formulated, to match each satellite to the visible satellite on the ground. Upon receipt of user data, each satellite then forwards the data only to the set of visible satellites that correspond to its own satellite. To validate the efficacy of IFAR, we conduct extensive simulation work, and the experimental results showcase the potential of IFAR to enhance the routing capabilities of LEO satellite networks and improve the overall quality of space-based internet access services.

Low earth orbit (LEO) satellite networks can provide Internet service to users in areas where cellular networks are difficult to deploy. One critical function of satellites is to transfer data from satellite networks to ground core network through earth stations (ESs). The Ka-band multiple-input multiple-output (MIMO) can be used to establish feeder links with larger bandwidth between satellites and ESs. However, propagation at the Ka band is subjected to rain attenuation and various atmospheric fading mechanisms, which severely reduce the maximum link capacity. As a result, the insufficient capacity of feed link becomes the throughput bottleneck of satellite networks. In order to increase network throughput, it is important to fully use feeder link resources. In this paper, we propose a cooperation scheme to route packets to ESs through a well-resourced feeder link, such that the bandwidth of the feeder links can be fully utilized and the throughput of data downloading at the ESs is maximized. Firstly, we model the satellite network system and the feeder link based on MIMO technology. Then, a Maximum-Flow-Minimum-Cost (MCMF) routing algorithm consisting of two Linear Programs (LPs) is presented to compute maximum-flow routings for data download. Eventually, a variety of simulations are conducted to assess the proposed scheme, which shows that the cooperative routing scheme outperforms the existing SiRRS method in terms of throughput and delay.

Fast convergence routing is an important issue for LEO constellation network, due to its dynamical topology changing and time varying transmission requests. Most of existing research focus on the OSPF routing algorithm, which cannot handle the frequently links state changing of network. In this paper, we propose a Fast-Convergence Reinforcement Learning Satellite Routing Algorithm (FRL-SR) for LEO satellite networks, in which the satellite gets the network links status fast and adjusts its routing strategy. In FRL-SR, each satellite node is regarded as an agent. The agent selects the port for packet forwarding according to its own routing policy. When the satellite network state changes, agent would send ’hello’ packets to the neighbor node to update the neighbor node’s routing policy. Compared with traditional reinforcement learning, FRL-SR can perceive network information faster, and then converge faster. Also, FRL-SR can mask the dynamics of satellite network topology and adaptively adjust the forwarding strategy according to the link state. Various simulation is constructed, the results show that the proposed FRL-SR algorithm out performance the Dijkstra algorithm in performance of average delay, packet arriving ratio, network load balance.