Collaborative Inference in DNN-based Satellite Systems with Dynamic Task Streams
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917024783925248 |
|---|---|
| author | Guan, Jinglong Zhang, Qiyang Murturi, Ilir Donta, Praveen Kumar Dustdar, Schahram Wang, Shangguang |
| author_facet | Guan, Jinglong Zhang, Qiyang Murturi, Ilir Donta, Praveen Kumar Dustdar, Schahram Wang, Shangguang |
| contents | As a driving force in the advancement of intelligent in-orbit applications, DNN models have been gradually integrated into satellites, producing daily latency-constraint and computation-intensive tasks. However, the substantial computation capability of DNN models, coupled with the instability of the satellite-ground link, pose significant challenges, hindering timely completion of tasks. It becomes necessary to adapt to task stream changes when dealing with tasks requiring latency guarantees, such as dynamic observation tasks on the satellites. To this end, we consider a system model for a collaborative inference system with latency constraints, leveraging the multi-exit and model partition technology. To address this, we propose an algorithm, which is tailored to effectively address the trade-off between task completion and maintaining satisfactory task accuracy by dynamically choosing early-exit and partition points. Simulation evaluations show that our proposed algorithm significantly outperforms baseline algorithms across the task stream with strict latency constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_06073 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Collaborative Inference in DNN-based Satellite Systems with Dynamic Task Streams Guan, Jinglong Zhang, Qiyang Murturi, Ilir Donta, Praveen Kumar Dustdar, Schahram Wang, Shangguang Distributed, Parallel, and Cluster Computing As a driving force in the advancement of intelligent in-orbit applications, DNN models have been gradually integrated into satellites, producing daily latency-constraint and computation-intensive tasks. However, the substantial computation capability of DNN models, coupled with the instability of the satellite-ground link, pose significant challenges, hindering timely completion of tasks. It becomes necessary to adapt to task stream changes when dealing with tasks requiring latency guarantees, such as dynamic observation tasks on the satellites. To this end, we consider a system model for a collaborative inference system with latency constraints, leveraging the multi-exit and model partition technology. To address this, we propose an algorithm, which is tailored to effectively address the trade-off between task completion and maintaining satisfactory task accuracy by dynamically choosing early-exit and partition points. Simulation evaluations show that our proposed algorithm significantly outperforms baseline algorithms across the task stream with strict latency constraints. |
| title | Collaborative Inference in DNN-based Satellite Systems with Dynamic Task Streams |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2311.06073 |