Towards Space-Based Computing Infrastructure Network: Development Trends, Network Architecture, Challenges Analysis, and Key Technologies

TL;DR

The paper addresses the bottleneck of ground-based data transmission in space remote sensing within the 6G era. It proposes a hierarchical space-based computing infrastructure that enables on-orbit data processing via a space-based cloud constellation, remote sensing constellation, NOCC, ODC, and UAP. It analyzes three core challenges—resource characterization/virtualization, multi-priority resource orchestration, and rapid resource sharing for bursts or failures—and outlines three technology pillars to tackle them: discovery/virtualization, orchestration/management, and fault isolation/security. The work highlights practical considerations and future research directions, illustrated by progress on TSN-01, toward AI-enabled autonomous on-orbit collaboration and multi-source information fusion.

Abstract

As one of the most promising hotspots in the 6G era, space remote sensing information networks play a key and irreplaceable role in areas such as emergency response and scientific research, and are expected to foster remote sensing data processing into the next generation of killer applications. However, due to the inability to deploy ground communication stations at scale and the limited data transmission window, the traditional model for transmitting space data back to ground stations faces significant challenges in terms of timeliness. To address this problem, we focus on the emerging paradigm of on-orbit space data processing, taking the first step toward building a space-based computing infrastructure network. Specifically, we propose a hierarchical space-based computing network architecture that integrates the space-based cloud constellation system, the remote sensing constellation system, the network operation control center, the orchestration data center and the user access portal, offering a detailed description of their functionalities. Next, we analyze three scientific challenges: the characterization and virtualization of multidimensional heterogeneous resources, the efficient orchestration of multidimensional heterogeneous resources for tasks with varying priorities, and the rapid sharing of multidimensional heterogeneous resources to address burst tasks or system failures. Finally, we discuss key technologies to address the aforementioned challenges and highlight promising research priorities for the future.

Figures (8)

• Figure 1: Hierarchical Space-Based Computing Network Architecture.
• Figure 2: Satellite Configuration.
• Figure 3: Characterization Dimensions for Multidimensional Heterogeneous Resources.
• Figure 4: The Impact of Virtualization Granularity on Resource Utilization Efficiency.
• Figure 5: Two Emergency Response Strategies for Burst Tasks and System Failures.