Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.11853 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917723849621504 |
|---|---|
| author | Wang, Meiqi Qiu, Han Xu, Longnv Wang, Di Li, Yuanjie Zhang, Tianwei Liu, Jun Li, Hewu |
| author_facet | Wang, Meiqi Qiu, Han Xu, Longnv Wang, Di Li, Yuanjie Zhang, Tianwei Liu, Jun Li, Hewu |
| contents | We are witnessing a surge in the use of commercial off-the-shelf (COTS) hardware for cost-effective in-orbit computing, such as deep neural network (DNN) based on-satellite sensor data processing, Earth object detection, and task decision.However, once exposed to harsh space environments, COTS hardware is vulnerable to cosmic radiation and suffers from exhaustive single-event upsets (SEUs) and multi-unit upsets (MCUs), both threatening the functionality and correctness of in-orbit computing.Existing hardware and system software protections against radiation are expensive for resource-constrained COTS nanosatellites and overwhelming for upper-layer applications due to their requirement for heavy resource redundancy and frequent reboots. Instead, we make a case for cost-effective space radiation tolerance using application domain knowledge. Our solution for the on-satellite DNN tasks, \name, exploits the uneven SEU/MCU sensitivity across DNN layers and MCUs' spatial correlation for lightweight radiation-tolerant in-orbit AI computing. Our extensive experiments using Chaohu-1 SAR satellite payloads and a hardware-in-the-loop, real data-driven space radiation emulator validate that RedNet can suppress the influence of radiation errors to $\approx$ 0 and accelerate the on-satellite DNN inference speed by 8.4%-33.0% at negligible extra costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11853 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Case for Application-Aware Space Radiation Tolerance in Orbital Computing Wang, Meiqi Qiu, Han Xu, Longnv Wang, Di Li, Yuanjie Zhang, Tianwei Liu, Jun Li, Hewu Emerging Technologies We are witnessing a surge in the use of commercial off-the-shelf (COTS) hardware for cost-effective in-orbit computing, such as deep neural network (DNN) based on-satellite sensor data processing, Earth object detection, and task decision.However, once exposed to harsh space environments, COTS hardware is vulnerable to cosmic radiation and suffers from exhaustive single-event upsets (SEUs) and multi-unit upsets (MCUs), both threatening the functionality and correctness of in-orbit computing.Existing hardware and system software protections against radiation are expensive for resource-constrained COTS nanosatellites and overwhelming for upper-layer applications due to their requirement for heavy resource redundancy and frequent reboots. Instead, we make a case for cost-effective space radiation tolerance using application domain knowledge. Our solution for the on-satellite DNN tasks, \name, exploits the uneven SEU/MCU sensitivity across DNN layers and MCUs' spatial correlation for lightweight radiation-tolerant in-orbit AI computing. Our extensive experiments using Chaohu-1 SAR satellite payloads and a hardware-in-the-loop, real data-driven space radiation emulator validate that RedNet can suppress the influence of radiation errors to $\approx$ 0 and accelerate the on-satellite DNN inference speed by 8.4%-33.0% at negligible extra costs. |
| title | A Case for Application-Aware Space Radiation Tolerance in Orbital Computing |
| topic | Emerging Technologies |
| url | https://arxiv.org/abs/2407.11853 |