With the continuous expansion of low-Earth-orbit (LEO) satellite networks, the services within these networks have exhibited diverse and differentiated demand characteristics. Due to the limited onboard resources, efficient network resource allocation is required to ensure high-quality network performance. However, the dynamic topology and differentiated resource requirements for diversified services pose great challenges when existing resource awareness or prediction methods are applied to satellite networks, resulting in poor awareness latency and the inaccurate prediction of resource status. To solve these problems, a network resource allocation method based on awareness–prediction joint compensation is proposed. The method utilizes the node awareness latency as a prediction step and employs a long short-term memory model for resource status prediction. A dynamic compensation model is also proposed to compensate for the prediction results, which is achieved by adjusting compensation weights according to the awareness latencies and prediction accuracies. Furthermore, an efficient, accelerated alternating-direction method of multipliers (ADMM) resource allocation algorithm is proposed with the aim of maximizing the satisfaction of service resources requirements. The simulation results indicate that the relative error between the compensation data and onboard resource status does not exceed 5%, and the resource allocation method can improve the service resource coverage by 15.8%, thus improving the evaluation and allocation capabilities of network resources.

Satellite communication networks, characterized by the advantages of seamless global coverage and ubiquitous access, have emerged as a main focus of current research. However, satellite network topology changes dynamically and burst traffic is spatio-temporal coupling, causing the satellite network traffic sensing problem with high overhead and low accuracy. Therefore, this paper proposes a spatio-temporal graph neural network-based satellite network traffic sensing approach (STSA) to collect data efficiently and predict traffic precisely. The study designs in-band network telemetry (INT)-based Hamilton cycle to reduce the number of repeated visits to satellite nodes, reducing the redundancy of data collection, and construct spatio-temporal graph of satellite network topology and traffic. STSA takes full advantage of the spatio-temporal dependence of topology and traffic to realize satellite network traffic sensing. The satellite network state view is generated by mapping the spatio-temporal characteristics of historical traffic to the next period. Simulation shows that STSA effectively reduces sensing overhead and improves accuracy compared to the traditional traffic sensing algorithm based on the Euler cycle and long short-term memory (LSTM). The proposed STSA provides traffic data for satellite network routing, enhancing the efficiency of satellite network management and control.