Task Scheduling in Space-Air-Ground Uniformly Integrated Networks with Ripple Effects

TL;DR

This paper addresses task scheduling in SAGUIN under ripple-like spatiotemporal interference. It first formulates the problem as an $MDP$ to minimize AoI and AP energy, then reformulates to a Markov Game to cope with high dimensionality and partial observations, solved by a modified MAPPO algorithm. The authors design an actor-critic architecture with local observations and a global critic, along with an offline training/online deployment pipeline, and demonstrate substantial improvements in AoI and energy across multiple network scales and configurations. The work provides a practical framework for cross-layer, interference-aware scheduling in next-generation unified space-air-ground networks, with potential impact on 6G-era global connectivity and latency-sensitive applications.

Abstract

Space-air-ground uniformly integrated network (SAGUIN), which integrates the satellite, aerial, and terrestrial networks into a unified communication architecture, is a promising candidate technology for the next-generation wireless systems. Transmitting on the same frequency band, higher-layer access points (AP), e.g., satellites, provide extensive coverage; meanwhile, it may introduce significant signal propagation delays due to the relatively long distances to the ground users, which can be multiple times longer than the packet durations in task-oriented communications. This phenomena is modeled as a new ``ripple effect'', which introduces spatiotemporally correlated interferences in SAGUIN. This paper studies the task scheduling problem in SAGUIN with ripple effect, and formulates it as a Markov decision process (MDP) to jointly minimize the age of information (AoI) at users and energy consumption at APs. The obtained MDP is challenging due to high dimensionality, partial observations, and dynamic resource constraints caused by ripple effect. To address the challenges of high dimensionality, we reformulate the original problem as a Markov game, where the complexities are managed through interactive decision-making among APs. Meanwhile, to tackle partial observations and the dynamic resource constraints, we adopt a modified multi-agent proximal policy optimization (MAPPO) algorithm, where the actor network filters out irrelevant input states based on AP coverage and its dimensionality can be reduced by more than an order of magnitude. Simulation results reveal that the proposed approach outperforms the benchmarks, significantly reducing users' AoI and APs' energy consumption.

Figures (13)

• Figure 1: Architecture of SAGUIN.
• Figure 2: Coverage properties of different APs in SAGUIN.
• Figure 3: Frame structure in SAGUIN.
• Figure 4: Example of the spatial and temporal interferences in task-oriented communications within SAGUIN. When satellite $k_1$ transmits data over channel $p$ to its covered user $u$, the signal propagates downward and interferes with other APs that are simultaneously using the same channel $p$ to serve the same user $u$.
• Figure 5: Interferences in SAGUIN.