GPR Hierarchical Synergistic Framework for Multi-Access MPQUIC in SAGINs

TL;DR

This paper introduces a novel hierarchical framework combining multipath scheduling and congestion control for MPQUIC in SAGINs, effectively addressing OFO issues and improving network performance in high-mobility environments.

Contribution

It presents the first joint optimization framework with predictive and proactive algorithms tailored for dynamic SAGIN scenarios, enhancing data transmission reliability.

Findings

Significant increase in goodput compared to baselines.

Marked reduction in out-of-order packet delivery.

Effective proactive handover and congestion management.

Abstract

The deployment of Multipath QUIC (MPQUIC) in Unmanned Aerial Vehicle (UAV)-assisted Space-Air-Ground Integrated Networks (SAGINs) is severely hampered by the out-of-order (OFO) packet delivery problem. Frequent stream handovers, high mobility, and massive multi-access contention in these networks introduce severe transport-layer challenges. Existing solutions typically isolate multipath scheduling from congestion control, which leads to suboptimal performance and transient congestion in highly dynamic environments. To overcome these limitations, this paper proposes the GPR Hierarchical Synergistic Framework, representing the first joint optimization of multipath scheduling and congestion control for multi-access MPQUIC in SAGINs. Our framework introduces the GradNorm Probabilistic Self-Predictive (GPASP) module to forecast latent states and filter task-irrelevant information in high-dimensional, noisy observation spaces. Furthermore, we develop a Proactive Handover-Aware Congestion Control (PHACC) algorithm that leverages neural network-driven decisions to proactively distinguish handover-induced packet losses from actual network congestion. To address decision-making lag caused by neural network inference latency, a Neural-network Preference Estimation (NNPE) algorithm is designed for highly efficient, real-time scheduling. Extensive ns-3 simulations demonstrate that the proposed framework significantly outperforms state-of-the-art baselines, achieving substantial goodput improvements and a marked reduction in OFO degrees.