Abstract
The spatial topology of large-scale low-Earth-orbit satellite communication networks is dynamically time-variant, and the load on the output ports of network nodes is continuously changing. The lengths and numbers of output port queues at each network node can affect the packet loss rate and end-to-end latency of traffic flows. In order to provide high-quality satellite communication services, it is necessary to schedule and optimize the lengths and numbers of queues used for transmitting time-sensitive traffic flows at each node's output port to achieve the best deterministic transmission performance. This paper introduces a queue scheduling optimization mechanism based on the Particle Swarm Optimization algorithm (PSO-QSO) for large-scale low-Earth-orbit satellite communication networks. This method analyzes the relevant parameters of various traffic flows transmitted through the network and calculates the maximum time-sensitive business load within network nodes. It applies the Particle Swarm Optimization algorithm to calculate the optimal solution for the length and number of queues at each node's output port used for forwarding time-sensitive traffic flows. The mechanism proposed in this paper ensures the deterministic end-to-end transmission of time sensitive traffic in large-scale low-Earth-orbit satellite communication networks and can provide real-time satellite communication services.