High-Performance On-Orbit Intelligent Computing and Real-Time Services for Remote Sensing Satellites Based on Large-Scale Computing Power in Space
The rapid advancement in Earth observation systems and satellite networks driven by commercial space has led to a significant increase in the number of remote sensing satellites, thereby establishing the groundwork for all-weather, continuous, cluster-collaborative observation. Following anti-irradi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11015791/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The rapid advancement in Earth observation systems and satellite networks driven by commercial space has led to a significant increase in the number of remote sensing satellites, thereby establishing the groundwork for all-weather, continuous, cluster-collaborative observation. Following anti-irradiation hardening measures, low-cost commercial off-the-shelf (COTS) devices are effectively operated within intricate space environments, leading to substantial enhancements of the on-orbit computing capabilities of individual satellites. The onboard-distributed processing framework can be leveraged to fully utilize wide-area scattered space computing resources; accordingly, it is possible to automatically establish a network of neighboring satellites through inter-satellite communication links to construct a spatially distributed and computationally cooperative cloud computing environment in space. This enables the sharing of space computing resources and facilitates satellite-based mission coordination, reducing reliance on ground-based remote sensing satellite services while enhancing the response efficiency of remote sensing application services. The present paper provides a comprehensive review of the current development status, existing challenges, and problems faced by space-based, on-orbit remote sensing processing platforms and onboard intelligent processing algorithms; we start with the immediate application requirements of the remote sensing satellites used in in-orbit processing. In view of the anticipated surge in large-scale computing resources in space, a distributed processing architecture for remote sensing satellite data, based on large-scale onboard computing power, is constructed. The architecture is designed in detail, with attention paid to the physical architecture, the software architecture, the workflow, and the key technologies. Finally, three real-time service scenarios that align with the construction content of an ultra-low-orbit satellite constellation and 6G technology have been designed to provide solutions and references for the subsequent development of space-based intelligent remote sensing constellations. |
|---|---|
| ISSN: | 2169-3536 |