A GNN-Enabled Multipath Routing Algorithm for Spatial-Temporal Varying LEO Satellite Networks.

Low Earth Orbit (LEO) satellite networks have recently been regarded as a promising solution to provide ubiquitous user access and flexible content delivery. To meet the increasing demands of satellite services, multipath routing is leveraged to transmit each flow via multiple transmission paths concurrently. However, dynamically changed satellite topologies have brought challenges to multipath route planning and traffic splitting among different paths. Thus, in the paper, we propose a GNN-enabled Multipath Routing (GMR) scheme to maximize the network efficiency. Particularly, we firstly formulate the mutipath routing issue as a stochastic optimization problem under the bandwidth limitation and flow conservation constraint, and further present a Link Disjoint Multipath Routing (LDMR) scheme for the central route calculation, where available transmission paths and uneven traffic density are jointly considered to maximize the link utilization. Then, to balance the load distribution of different paths, a GNN-based MultiPath Traffic Engineering (GNN-MPTE) algorithm is designed for dynamic flow splitting based on estimated path quality. Finally, we implement the proposed GMR scheme and corresponding algorithms in Network Simulator NS-3 and make comparisons with other benchmarks. Simulation results demonstrate that the proposed GNN-MPTE can be extended to arbitrary inclined/polar orbit constellations without repetitive training, and significantly prompt the transmission quality including average delay, throughput, and flow completion ratio.