Service-Driven Shared QoS Orchestration for Satellite-Ground Integrated Networks

Satellite and ground systems have traditionally operated independently, each providing unique services. However, the integration of satellite-ground networks necessitates collaboration to ensure consistent Quality of Service (QoS) for users in the Satellite-Ground Integrated Network (SGIN). This paper focuses on achieving highly reliable shared QoS orchestration for SGINs. We analyze eight typical SGIN services, including ultra-long-distance real-time, densely connected, high-speed mobile broadband, real-time large-capacity transmission, non-real-time large-capacity transmission, highly secure, deterministic guarantee transmission, and high-reliability guaranteed transmission services. The constantly changing SGIN topology, due to rapid inter-satellite link switching, prompts us to explore data-driven multi-service identification using Artificial Intelligence (AI) techniques. For accurate identification, two approaches are proposed in this paper: a Decision Tree (DT)-based scheme and an ensemble learning-based scheme. Additionally, we present the construction of a shared QoS system in SGINs, along with the evaluation and assurance of AI services using the concept of QoS of the SGIN AI service (QoSGINAI). Simulation results demonstrate the effectiveness of the proposed AI-based multi-service identification schemes.